Order 20260823T175853Z from .claude: commit 5870483 (the G3 nine-key
allowlist fix) was untagged -- llm-ingestion-okf measured 4/9 concepts
through Doer C on it, blocked from 8/9 only by the absence of a
pinnable tag, on a suite already green (595/596) at that commit.
Six live version surfaces bumped by hand (no sed -- provenance is
never bumped): pyproject.toml, __init__.__version__, README badge +
Status + the pinned pip install tag, docs/BRIEF.md, docs/ADOPTION-BRIEF.md
Status, and CLAUDE.md. ADOPTION-BRIEF's snapshot line moves with it:
129/129 -> 130/130 classes, 802 -> 834 passing (the new row is the
off-allowlist-key coverage case added by the G3 fix itself).
NOT bumped, matching the 1.1.0 precedent: every "closed in 1.1.0" /
"the 1.1.0 defect" reference across CHANGELOG.md, CLAUDE.md,
docs/LIMITATIONS.md, docs/redos-sweep.py, src/llm_ingestion_guard/okf.py
and tests/ names a historical baseline, not the current version --
rewriting those would erase what they document. docs/BRIEF.md's
GuardLLM v1.1.0 reference is a third party's version, untouched.
Re-measured after the bump, alone: 834 passed, 130/130 classes, 6/6
gaps hold, 43 limitations, ReDoS sweep 0/152 candidates flagged.
No exported surface changed; no detector behaviour and no calibration
changed. Pure release action -- no functional code touched.
OKF v0.2 writes its whole trust and provenance layer as mappings, and T2 gave
the mapping class no expressible form. A consumer measured 0 of 53 upstream
concepts through the gate on 0.3.4, 1.0.0 and 1.1.0. That was a contract
collision, not a calibration setting: SPEC.md @ 62432a09 uses flow mappings in
its own 5.1/5.2 examples, and 11 carries a hard MUST for consumers ("MUST treat
a bare `verified` mapping as a one-element list") that presupposes they parse.
Admitted: a flow mapping, as a value or as a block-list item, whose every key is
on a nine-name allowlist and whose every leaf is a plain scalar run through the
unchanged dangerous-value and mapping-construct predicates. The form is safe
because the allowlist inspects every key -- the blanket refusal was the
enforcement, not the point.
Refused, each on its own rule and ground-truthed against PyYAML 6.0.3: a key off
the allowlist, a nested collection, a quoted leaf, a duplicate key, an empty or
unclosed mapping, trailing junk, and {a:b} (which PyYAML reads as the KEY a:b).
A refused mapping still raises rather than degrading into a string, so the 1.1.0
type-confusion defect is not reopened, and the block, dotted and inline-colon
routes still raise.
`resource` is deliberately off the allowlist though SPEC.md 5.1 names it inside
a `sources` entry: it is a pointer rather than a label and the only key T3
exists for, so admitting it would let `executor: { resource: skills/run.md }`
carry an executable-code pointer through in typed clothes -- the door-C route
closed in 1.1.0. It costs nothing today, because the conformant carrier for
sources[].resource is a block sequence of block mappings, which stays refused.
Mapping leaves are scanned like every other frontmatter value (T1). Coverage
matrix 130/130 (new row: the off-allowlist key). No exported surface, detector
behaviour or calibration changed.
Six live version surfaces bumped by hand (no sed -- provenance is never
bumped): pyproject.toml, __init__.__version__, README badge + Status + the
pinned pip install tag, docs/BRIEF.md, docs/ADOPTION-BRIEF.md Status, and
CLAUDE.md. ADOPTION-BRIEF's test count 792 -> 802.
NOT bumped, and deliberately: SECURITY.md's two `1.0.0` references name the
freeze BASELINE, not the current version -- "a payload that disposes WARN on
1.0.0 may dispose FAIL_SECURE on a later 1.x" is the promise this release
instantiates, so rewriting it to 1.1.0 would erase what it promised. The
GATE-G and PLAN-v1 numbers are the 1.0.0 gate record. The Forge repo
description carries no version (verified against the API last session).
This is the case SECURITY.md and the 1.0.0 CHANGELOG entry described in
advance: the exported surface is frozen, detection behaviour is not. No
exported name moved. A document that disposed WARN on 1.0.0 may dispose
FAIL_SECURE here; a consumer whose frontmatter carries an unquoted ": " in a
value will see those concepts refused at import, and quoting it parses.
Re-measured after the bump, alone: 802 passed, 129/129 classes, 6/6 gaps hold,
35 limitations.
T2 gives the mapping class no expressible form by design. Two routes escaped
that by parsing "successfully" into the wrong TYPE instead of raising:
sources:\n - uri: https://e.com/a -> the string 'uri: https://e.com/a'
attester: resource: attesters/x.py -> the string 'resource: attesters/x.py'
Only the first was documented (LIMITATIONS.md:43). The inline second colon was
found by measurement while closing it -- a real YAML parser refuses that line
outright, ours accepted it. Shipping the list half alone would have left a
LIMITATIONS rewrite that overclaims.
Same consequence either way: a pointer parked in a degraded mapping rides
through in a key the `resource` allowlist never inspects, and mode-b
import_bundle wrote the merged concept verbatim (WARN). Both now FAIL_SECURE at
T2, before the allowlist is reached.
The boundary is where YAML puts it, ground-truthed against PyYAML 6.0.3 rather
than reasoned: ": " and a trailing ":" are exactly the two shapes where a plain
scalar becomes a mapping. A colon carrying neither a space nor a line end opens
no mapping -- domain:security and https://e.com:8443/a still parse -- and a
quoted scalar is still a scalar. Over-blocking a conformant bundle is itself a
failure mode, so the seven admitted shapes get rows of their own.
Iron Law: the four rejected rows and both import_bundle rows were written
first and seen red (7 failures, each DID NOT RAISE) before okf.py was touched.
Suite 792 -> 802. LIMITATIONS stays at 35: the bullet is reworded, not
retired -- the restricted grammar is still a limitation, the silent misparse
is no longer part of it.
Nine current-state surfaces bumped by hand. The classification sweep ran
FIRST, before the first edit: 421 hits on 'v?0.N(.N)' across all tracked
files, each read and sorted current-state vs provenance. Provenance is
untouched -- 'New in v0.4.0', 'measured against 0.3.1', every '0.7.0'
in a code comment or a census candidate name still says what it measured.
The sweep found two surfaces the plan's nine-item list did not name:
README's status BADGE (still 'alpha' -- a version string grep cannot see
it) and ADOPTION-BRIEF's test count, which said 791 against a suite that
runs 792. Both corrected.
pyproject also moves Development Status :: 3 - Alpha -> 5 -
Production/Stable, likewise invisible to a version grep.
CHANGELOG [1.0.0] references [0.3.0] and [0.3.1] for the behaviour
changes rather than repeating them, and carries the freeze point itself:
what is frozen (the exported surface), what is deliberately NOT (all
detection calibration), the three conceded limitations, the one known
open defect (:43), and the runtime-coverage gap -- no external consumer
has run 0.7.0.
No code changed. Per docs/PLAN-v1.md the release gate is the whole suite
green, not a new test: 792 passed, coverage matrix 129/129 + 6/6, exit 0.
0.7.0 shipped with its corpus numbers deliberately absent: the census had only
run on reference-corpus, which the 0.6.0 narrowing had already emptied of
raw-HTML drivers, so it bounded the change rather than showing it. Both wiki
corpora are now measured through the pinned instrument, in one session because
they are living populations.
Under PRESET_USER_UPLOAD, 0.6.0 as shipped -> 0.7.0, each population against its
own denominator (the two wiki corpora share content and are never summed):
reference-corpus 389 docs 54 -> 53 ceiling 53
vendor-harvest 187 docs 62 -> 20 ceiling 18 42 of 44 achievable
generated-notes 552 docs 59 -> 15 ceiling 13 44 of 46 achievable
PRODUCTION matched C1 + D field for field in every population, which is the
check that the instrument and the shipped predicate have not drifted.
Two things the measurement changed rather than confirmed:
The pair is superadditive by 13 documents in BOTH wiki corpora. Alone, the split
frees 8 in each and the narrowing 21 and 23; together they free 42 and 44.
Shipping either alone would have measured as barely worth the label.
The TIGHTENS column reads 0 on both tiers in all three populations, but that zero
is empirical and thin: the split measured ALONE tightens 13 documents on the
trusted tier in vendor-harvest and 14 in generated-notes, and the narrowing
cancels each one. LIMITATIONS now says so explicitly, so nobody reads the zero as
'cannot happen' -- the escalation is still constructed and pinned by
test_split_tightens_the_trusted_tier_when_both_carriers_are_present.
generated-notes counted 552 documents, not the 550 the scratchpad probe saw.
Living corpus, measured fresh.
791 passed; coverage 129/129, 6/6 documented gaps hold.
Two changes that had to ship together, because they co-occur.
`active:raw-html-link` (MEDIUM) splits the click-required carriers out of
`active:raw-html`. The same URL was LOW as `[t](url)` and HIGH as
`<a href="url">` — an asymmetry produced by syntax, not by affordance, on a
carrier the markdown path has graded MEDIUM since 0.3.1. The event-handler test
runs first, so `<a onclick=...>` stays HIGH. The url-attribute branch stays HIGH
too: a name outside the active set has unknown rendering, and grading
`<Card src=...>` as a link would be reasoning rather than measurement.
The no-URL narrowing makes `</a>`, `<Frame>`, `<video />` and `<img alt=...>`
without `src` inert — `<base />`'s argument from 0.6.0 applied to the rest of the
name branch. It tests for the URL attribute's PRESENCE, not for a readable value,
so the fail-secure gap `_url_attr_is_external` leaves open is not reopened here.
WHY TOGETHER: the narrowing strips a document's `</a>`/`<Frame>` and what remains
is the `<a href=...>` the split grades down, so each alone leaves the document
blocked by the other's residue.
`active_tag_class` is now the classification point and `is_active_tag` wraps it.
The census patches the former: a boolean could only express a narrowing, never a
regrade, so every carrier candidate would have measured equal to PRODUCTION —
silently, and in the direction that reads as "no change helps".
TWO COSTS, BOTH RECORDED RATHER THAN GLOSSED:
- The split TIGHTENS the trusted tier. One finding becomes two, and >=2 findings
at MEDIUM+ trip the compound overlay, so a document carrying both an `<img src>`
and an `<a href>` goes WARN -> quarantine_review on PRESET_TRUSTED_SOURCE. On
that preset it is the only direction the split can move anything. The census
now reports a TIGHTENS column on both trust tiers against the previously
shipped row — "frees N" without "tightens M" is a one-sided number.
- `count` drops on documents containing `</a>`, a published field moving under a
meaning that did not change.
MEASURED: reference-corpus (389) 54 -> 53 fail_secure, tightens 0/0, and the
census `PRODUCTION` row equals its `C1 + D` candidate row for row. The census
also reproduces 133/3/13/108/25 exactly, so it is calibrated against every
published historical number. The two wiki corpora are NOT yet re-measured; the
tree says so explicitly in the docstring, LIMITATIONS and CHANGELOG rather than
carrying probe numbers as fact.
791 tests (was 759), coverage 129/129, 6/6 documented gaps holding. Version
bumped to 0.7.0 across every surface; no tag is set until the measurement lands.
a59184b fixed a hard-block that reached every emoji-composed document, and
llm-ingestion-okf was told so -- while the fix sat untagged on main. A consumer
cannot pin what has no tag, so the notice was a promise the repo had not kept.
SURFACES MOVED (the eight the 0.5.0 sweep established, plus the ninth verified)
pyproject.toml 0.6.0 -> 0.6.1
__init__.py 0.6.0 -> 0.6.1
CHANGELOG.md [0.6.1] entry, [Unreleased] reset to "Nothing yet."
README.md badge, install tag @v0.6.1
docs/ADOPTION-BRIEF.md `v0.6.0` x2, and 727 -> 736 passing
CLAUDE.md one clause: ZWJ judged by context, not identity
SECURITY.md `0.6.x` -- still true at 0.6.1, verified, not moved
docs/BRIEF.md `v0.6 (alpha)` -- likewise
README.md:36 `v0.6`, alpha -- likewise
forge description re-verified THIS release: 178 codepoints, no version
claim. Not inherited from 0.6.0's check.
PATCH, NOT MINOR -- and it was asked, not assumed. 6bcb898 made "loosens the
upload door" the criterion for minor, and this loosens it too, so the reading
was put to the operator with the count rather than settled quietly. 0.6.0 was a
policy choice (`<base>` left the active name set by decision); this restores a
contract the module already published, against a class never meant to be
blocked. Measured loosening: 1 document of 1126 across the three FP populations
(reference-corpus 1/389, vendor-harvest 0/187, generated-notes 0/550), against
0.6.0's 25 + 2 + 2. Operator chose patch.
VERIFIED ON THE BUMPED TREE, NOT THE PRE-BUMP ONE
736 passed; coverage 128/128 recall, 6/6 documented gaps hold
`git grep '0\.6\.0'` returns provenance only -- LIMITATIONS history, the
census script, source docstrings, tests, README's pre-0.6.0 numbers
docs/LIMITATIONS.md: 34 items, README says 34
__version__ and pyproject agree at 0.6.1
no tracked file carries a stale current-state version or test count
The sweep tool itself was wrong first: `git grep -E '\b727\b'` returns nothing,
because POSIX ERE has no `\b`. An empty result read as "clean" when the claim
was there. Every sweep above is plain `git grep`.
Still to prove before this is announced: a scratch-venv install at the tag with
the resolved version asserted -- the README line above is only true once v0.6.1
resolves.
`_ZERO_WIDTH` (sanitize, input) and `_ZERO_WIDTH_CPS` (output,
`_scan_invisible_carriers`) tested U+200D on codepoint membership alone.
`disposition._CARRIER_LABELS` grades both as any-tier FAIL_SECURE with no
appeal, so any first-party document containing a ZWJ-composed emoji --
professions, families, skin tones, flag variants -- was hard-blocked forever.
Reported by ms-ai-architect; confirmed here against the code.
The strip was the worse half and was not in the report: sanitize *removed* the
joiner, silently decomposing the emoji into two unrelated ones. A module whose
contract is "only ever removes carriers" was corrupting content.
The fix is the one our own lexicon row `unicode:zero-width-in-word` (`\w[ZW]\w`)
already used: judge the joiner by CONTEXT, not identity. A ZWJ is exempt only
when BOTH neighbours are emoji-context codepoints. Half-context is not context,
so `a<ZWJ>{emoji}` stays a carrier and an attacker cannot buy exemption with a
single emoji.
Blocks, not an emoji table. Measured against Unicode 17.0's
`emoji-zwj-sequences.txt`: 1614 RGI sequences use 122 distinct codepoints
adjacent to a ZWJ, and the five ranges cover 122/122. The measurement earned
its keep -- the hand-reasoned candidate table missed U+2194, U+2195 and U+2B1B.
Shipping the RGI list itself would be exact on the day it landed and stale at
the next Unicode release, reopening this same false positive for every new
emoji; whole blocks carry the unassigned headroom (458 Cn codepoints) that
future emoji are allocated into, so the table does not age.
The predicate is defined once in sanitize and imported by output. A second copy
is how the input side stops flagging while the output side keeps blocking; the
cross-surface test asserts the two agree on six inputs.
Two residuals, both in LIMITATIONS (33 -> 34, README bumped): a ZWJ between two
emoji is now exempt and could carry a covert channel (one emoji per bit, cannot
split a word); and U+200C (ZWNJ) still has no context test, so Persian, Arabic
and Devanagari documents -- where it is orthographically required -- stay
blocked. That needs a script-based criterion and no corpus is here to verify it
against, so it is parked as a known FP class rather than guessed at.
736 green (was 727), coverage 128/128, 6/6 documented gaps hold.
The narrowing landed in 736f370 and its prose asserted `0.6.0` in thirteen places
-- README's public front page among them -- while every version surface still read
0.5.0. That is the same defect class the last three commits were spent correcting:
a published number no measurement backs. Two ways out, land it or neutralize the
references; operator chose to cut.
SURFACES MOVED (the eight the 0.5.0 sweep established, plus the ninth verified)
pyproject.toml 0.5.0 -> 0.6.0
__init__.py 0.5.0 -> 0.6.0
CHANGELOG.md [Unreleased] -> [0.6.0], fresh [Unreleased]
README.md badge, `Status: v0.6`, install tag @v0.6.0
SECURITY.md support window `0.5.x` -> `0.6.x`
docs/BRIEF.md `v0.5 (alpha)` -> `v0.6 (alpha)`
docs/ADOPTION-BRIEF.md `v0.5.0` x2, and 717 -> 727 passing
CLAUDE.md `v0.5 (alpha)` -> `v0.6`, plus what 0.6.0 changed
forge description 178 codepoints, carries no version claim -- verified,
not moved. A surface can be checked and stay still.
Measurement provenance is left alone, as in 0.5.0: `tests/test_disposition.py`'s
"0.5.0 axis separation", `disposition.py` and `calibration.py` docstrings,
LIMITATIONS' 0.5.0 reference, every dated claim in docs/PLAN-v1.md. Bumping those
falsifies the record rather than updating it.
MINOR, NOT PATCH: 0.6.0 loosens the upload door. A document whose only finding was
a doc-relative URL attribute on an inactive tag name, or an attribute-less
`<base />`, now WARNs where it was held -- 25 documents in the reference corpus, 2
in each wiki corpus.
VERIFIED BEFORE COMMITTING, NOT AFTER
727 passed; coverage 128/128 recall, 6/6 documented gaps hold
docs/LIMITATIONS.md: 33 items, README says 33
rawhtml-census PRODUCTION row equals `A + base-url` on all three populations --
the shipped predicate measured, not a hypothesis about it
redos-sweep: 0 candidates of 152 patterns
docs/fp-sweep.py still imports the private names it reaches into
no tracked file carries a stale current-state version claim
Still to prove before the tag: `git show` over this commit's README, and a clean
clone install at this sha.
`is_active_tag`'s URL-attribute branch was a presence test: any element carrying
`href=`/`src=`/`action=` graded HIGH regardless of where the URL pointed. An MDX
`<Card href="/en/agent-sdk/quickstart">` reaches no attacker-controlled host, and
neither does APIM policy XML's `<set-header>`. It now requires an external target
-- the rule the markdown paths have applied since 0.3.1. `<base>` left the active
name set in the same change: HTML's `<base>` has its whole affordance in an `href`
the attribute branch still catches, and APIM's attribute-less `<base />` is inert.
Measured before and after in ONE session against one corpus state, because two of
the three corpora are living and a split would mix this with re-harvest drift:
reference-corpus 389 docs 133 -> 108 (ceiling 107)
vendor-harvest 187 docs 100 -> 98 (ceiling 62)
generated-notes 550 docs 90 -> 88 (ceiling 49)
96% of the achievable reduction in reference-corpus, 5% in the wiki corpora. The
two classes had to be measured TOGETHER -- alone they free 3 and 13 documents,
together 25, because a document carrying one usually carries the other.
The second surface: `neutralize` imported `is_active_tag` by name, so this would
have silently narrowed the opt-in mutator too -- and no test discriminated the two
halves, since every `neutralize:raw-html` payload stays active under any narrowing
considered. That test is written first here. The predicates are now separate
symbols; the mutator keeps defanging anything, because over-defanging is auditable
and blocks nothing while under-defanging hands a human a live construct.
Behaviour change: a document whose only finding was one of these classes now WARNs
instead of holding. Detection is unchanged -- 128/128 classes, 6/6 gaps hold.
Self-safety: reading an attribute VALUE needs a pattern the presence test lacks. It
reuses the same literal alternation so no new run shape enters the table; its
`_REDOS_PAYLOADS` row denies the `=` the pattern requires, since a unit supplying it
matches at once and never exercises the run (the lexicon's `script-tag` row is the
cautionary case). 0.031-0.046s across five attack shapes at 100_000 chars against a
2.0s bound; `docs/redos-sweep.py` reports 0 candidates of 152. An attribute the
presence test saw but the value parser cannot read counts as external -- fail secure.
`docs/rawhtml-census.py` gains a PRODUCTION row that re-measures the shipped
predicate rather than a hypothesis, so a published number and the code cannot drift
apart unnoticed. README's limitation count moves 34 -> 33.
727 passed (was 717).
0.5.0 is the axis separation `de09711` built: `Risk` (assessment) alongside
`Disposition` (action), `Policy.action_map` as the supported override, and the
fail-closed path pinned to both axes. Additive and measured to be so — 717
passing with no test changed, matrix 128/128 with 6/6 documented gaps, the
`PRESET_USER_UPLOAD` grading table unchanged row by row. Plus the field FP
measurement (`d1bff60`) and the 0.3.3 behaviour-change correction (`d3d0928`).
WHY THIS COMMIT TOUCHES EIGHT FILES AND 0.4.0's TOUCHED THREE
0.4.0's release commit updated CHANGELOG, pyproject.toml and __init__.py, and
deferred README deliberately: the install block should not name a tag before a
clean-venv install had proven it resolved. Sound reasoning, and the proof step
never ran — so tag v0.4.0 permanently advertises v0.3.4. The tag is not moved.
The ordering is.
Sweeping every tracked file for a version claim, instead of ticking the four
surfaces the checklist named, found five more that no release had ever touched:
SECURITY.md "pre-1.0 (0.2.x)" — the one with a consequence for an
outsider: it named a support window two minor lines
behind the code.
README.md "**Status:** v0.3" — the front page, stale since 0.4.0.
docs/BRIEF.md "v0.2 (alpha)" — stale since 0.3.0.
CLAUDE.md "v0.2 (alpha)" and "12 moduler" where src/ has 15.
docs/ADOPTION-BRIEF "703 passing" where the suite is at 717.
Measurement provenance is deliberately left alone: "New in v0.4.0", "verified
identical on 0.2.0 and 0.3.1", "measured against the v0.3.1 tag", every
"post-0.4.0 tree" in LIMITATIONS. Bumping those falsifies the record instead of
updating it, which is why this cannot be a sed sweep — the surfaces have to be
sorted into current-state and provenance before a single edit.
Found because llm-ingestion-okf took our report of this defect class as a
hypothesis about their own repo, measured it, found a worse instance on their
public front page, and sent back the generalization: writing down a trap is not
the same as applying it.
VERIFIED BEFORE COMMITTING, NOT AFTER
717 passed; coverage 128/128 recall, 6/6 documented gaps hold
docs/LIMITATIONS.md: 33 items, README says 33
fp-sweep reproduced all three published numbers exactly on the bumped tree —
vendor-harvest 98/185 (53.0%), generated-notes 88/547 (16.1%),
reference-corpus 133/389 (34.2%) — and self-docs runs clean, so the
untested script survived the bump it imports names from
forge description: 178 codepoints, under the 180 cap
no tracked file carries a stale current-state version claim
Still to prove before the tag: a clean-venv install from this commit's sha, and
`git show <sha>` over the README. The install proves the package builds; only
the grep proves the text the tag will carry is right. That second check is the
one the old ordering could not perform, because by then the tag existed.
`decide` returned a `Disposition` — WARN / QUARANTINE_REVIEW / FAIL_SECURE —
which names an ACTION. But BRIEF design principle 4 says the library reports
and the pipeline decides, and disposition.py admitted the gap in its own
docstring: "It imposes no blocking of its own." So we returned an action we
cannot enforce, having discarded the judgement that produced it. A consumer
wanting different behaviour had to reinterpret the action itself — which is
why a consumer ends up pinning our GRADING: the action was all they got.
`Risk` (NONE/LOW/ELEVATED/SEVERE) now carries that judgement, and
`Policy.action_map` lets a caller map it to their own action. Both overlays
move the assessment rather than the action, so a custom map cannot silently
drop the compound escalation or the quarantine floor. `guard`'s fail-closed
path pins both axes and deliberately bypasses the map: downgrading SEVERE
means "I accept this class of finding", never "I accept a crashed scanner".
`DispositionResult.assessment` is required with no default. `Risk.NONE` is the
natural-looking default and the wrong one — a site that forgot the field would
report clean, and the axis would fail open.
MEASURED ADDITIVE, not assumed:
- 703 -> 715 tests, no existing test changed
- coverage matrix 128/128 recall, 6/6 documented gaps still hold
- the PRESET_USER_UPLOAD grading table locked in 0.3.1 re-measured row by
row: ordinary link/image/autolink/refdef -> warn on BOTH doors, unchanged
Both locked consumer promises in docs/PLAN-v1.md were checked against that
measurement and neither fires: the grading is untouched (linkedin-studio), and
the relative-target asymmetry is untouched (llm-ingestion-okf).
Scope held to disposition, per PLAN-v1.md:380. Version stays 0.4.0; the 0.5.0
bump lands in its release commit with all five version surfaces at once —
that is the fix for the defect where the v0.4.0 tag carried a 0.3.4 README.
Records limitation 32: `Severity` still carries disposition intent on the
DETECTION side, which this change does not address and cannot without moving
the grading.
okf answered the exposure question with a measured no — zero call sites for the
three capped surfaces anywhere in their src/, and their screen_output path
reaches only scan_output, which truncates. So the blast radius is zero and 0.3.5
would have hurt nobody.
It is still 0.4.0. Adding a raise to a previously total public function is
breaking under SemVer, and this file declares SemVer; a survey that comes back
clean tells you the upgrade is easy, not that the contract held. The version
number describes the change, not the luck of who happens to call it.
Cost, stated: 0.4.0 was penciled in for the axis separation. That moves to 0.5.0.
Tags are never moved, so the choice is made once.
README still advertises v0.3.4 — it is updated after a clean-venv install proves
the tag resolves, so the install block never points at something unproven.
`scan_active_content` called directly and `okf.link_graph` were the two surfaces
still reading attacker-supplied text with no cap — the first reached by an
adapter that wants the active-content classes alone, the second running a
`findall` over every body in a bundle. Both are detection-shaped, so they
truncate and flag rather than raise the way the transform surfaces do: what a
detector shortens is its own coverage, not the caller's content.
Truncation is only honest if it is visible, so neither goes quiet: the scanner
emits `active:oversize-input` (LLM10), and `link_graph` records
`(from_id, body_length)` in `LinkGraphResult.truncated` — the field that lets a
caller tell "no links past here" from "no links read past here".
Reached through `scan_output`, the text is already under that surface's cap and
`max_scan_chars` is now passed down, so the flag is raised once, there.
The scanners cap by truncating: they return findings, so reading a prefix costs
detection in the tail and nothing else. The three transform surfaces return
*content*, where the same move is not available — a shortened document is silent
data loss, and a transformed prefix followed by an untransformed tail is a
bypass, since the attacker chooses where in the document the payload sits.
So they fail secure instead. Above MAX_INPUT_CHARS (1 000 000) sanitize, fence
and neutralize raise OversizeInputError. sanitize is step 1 of prepare_input and
only ever removes, so that one refusal bounds the whole input path.
OversizeInputError subclasses ContractViolation: a pipeline already bracketing
its quarantined stage keeps failing closed rather than meeting a type it has
never heard of. It inherits the alert-routable property too — sizes in the
message, refusing surface in details, no input in either.
Invariant now pinned across all three: returned text is always fully
transformed, or not returned at all.
Still uncapped and recorded in LIMITATIONS: scan_active_content called directly
(through scan_output it inherits that cap) and the okf link graph. Both are
detection-shaped, so truncate-and-flag transfers unchanged — mechanical, not
policy.
699 tests (+23), coverage 128/128 + 6/6, ReDoS sweep 0 candidates / 150.
0.3.3 swept 83 lexicon patterns arm by arm and left the other ten regex-bearing
modules on 0.3.2's hand-written rows. Generalising the sweep found three more,
and the two on the input path matter more than the count suggests: `sanitize` is
step 1 of `prepare_input`, and `MAX_SCAN_CHARS` is applied in `scan_lexicon` and
`scan_output` only, so there was no cap to extrapolate to. That missing input
cap is now a documented residual of its own -- extending it changes the contract
for existing callers and is not something to smuggle into a ReDoS patch.
Version synced in all four places + CHANGELOG. LIMITATIONS 30 -> 31 items;
the 0.3.3 entry claiming the lexicon sweep's scope is corrected in place, since
"the output path" was never the whole surface either.
676 tests, coverage 128/128 + 6/6 gaps, sweep clean across 150 patterns.
The generalised sweep found what 0.3.2's hand-written rows missed. All three are
the documented class -- a run in front of a required literal that never arrives,
so every start position rescans the tail -- and all three are worse than the
0.3.3 findings, because `sanitize`, `neutralize`, `scan_active_content` and the
okf link graph apply NO input cap. `scan_lexicon`/`scan_output` are the only
entry points that do, so there is no ceiling to extrapolate to.
sanitize._HTML_COMMENT_RE `<!--`*100_000 20.1s, exponent 1.96-2.14
active_content.URL_IN_TEXT_RE `<a `+`A`*100_000 12.99s / 14.9s, exponent ~2.0
okf._MD_LINK_RE `[`*100_000 7.1s, exponent 1.99-2.05
Each fix is the one the pattern's own shape allows, not a copied choice:
- The comment stripper drops the regex for `str.find`. Excluding `<` would lose
every comment containing markup; bounding the run would be a carrier bypass
of the exact construct the stripper exists to remove.
- `URL_IN_TEXT_RE` bounds its scheme run to an RFC 3986 scheme (`{0,63}`).
Bounding is safe *here* only because it is a defanger inside a tag already
flagged `active:raw-html`. A lookbehind was measured too and rejected: it
drops `-http://evil.com`, a one-character evasion. Bounded: 0.185s at 1M.
- `_MD_LINK_RE` excludes `[`, matching `active_content.MD_LINK_RE` exactly,
including the nested-label trade already documented there.
`sanitize` claimed "no catastrophic backtracking" in a comment; that claim was
wrong in the same way `output`'s was before 0.3.2, and is corrected in place.
676 tests (+10), coverage 128/128 + 6/6 gaps, sweep clean across 150 patterns.
The okf destination run gets no row: `[^)\s]+` cannot fail, so a row for it
could never go red.
Version synced across the four locked points (pyproject, __version__, README
badge, README install pin) + CHANGELOG.
Corrections this release carries, both measured rather than reasoned:
- docs/LIMITATIONS.md said the script-tag change removed "the last"
quadratic-backtracking site on the output path. It did not. Corrected, with
the 334.7s gate measurement that falsifies it.
- README's coverage line claimed 126/126 classes; the matrix reports 128/128.
Stale since before v0.3.2. Test badge was 642, actual 666.
New residual recorded (LIMITATIONS, now 30 items, README synced): the sweep
flags on timing above a 1.5ms noise floor at N=8000, so an arm hiding under it
could still cost ~23s at the cap. What this supports is "no arm worse than ~23s",
not "no quadratic arm remains" -- and the blind spot is demonstrated, since a
generic-payload pass found only one of the two patterns.
666 tests green, coverage matrix 128/128 with 6/6 gaps holding, exit 0.
The input-path duty `8deca93` scoped. All 83 lexicon patterns measured arm by
arm; two are quadratic, same shape 0.3.2 fixed -- a run in front of a required
literal that may cross the pattern's own opening anchor. Exponent 1.98 over five
points, so quadratic, not exponential.
markdown:link-anchor-injection `[` 1.91s @8k ~8.3h at the cap
markdown:link-anchor-injection `[system](` 0.006s @8k ~89s at the cap
markdown:link-ref-comment `[//]: # (` 0.22s @8k ~1.0h at the cap
Not input-path-only: `scan_lexicon` runs on the output path, so `scan_output("["
* 100_000)` took 334.7s. 0.3.2's "last quadratic site on the output path" was
false when written -- its sweep drove `[` only through `scan_active_content`.
Fix is anchor exclusion, not bounding (bounding attacker-controlled content is a
one-line bypass). The excluded char is `(`, not the obvious `[`: excluding `[`
drops `[//]: # (see [x] then ignore this)`, which no other pattern catches. The
anchors contain `(` too, so it telescopes at zero measured recall cost.
N is per row deliberately. The URL arm ran 0.9s UNFIXED at N=100_000 -- under the
2.0s bound, so that row could not have failed. Measured at N=300_000 instead,
where crafted (8.10s) and legitimate (0.926s) separate 8.8x.
Version sync in all four places (pyproject, __version__, README badge, README
install pin) plus the changelog entry for cff0437.
Two claims that were about to ship in the release note did not survive being
measured against a v0.3.1 worktree, and are corrected in LIMITATIONS first:
- "Report-only, so the cost is a review, not a block" was wrong twice. HIGH under
a low-trust preset is fail_secure, not a review -- report-only means the text is
never mutated, not that a finding cannot block. And the new script-tag false
positive costs no consumer a disposition at all: any text containing a literal
`<script>` already produced active:raw-html at HIGH on 0.3.1, so the same prose
disposed fail_secure under PRESET_USER_UPLOAD before this change and after it.
The fail-open that was closed is narrower for the same reason -- it existed only
in scan_lexicon called on its own; through either composed gate, raw-html
already caught the unclosed tag. What changed is the label, not the outcome.
- "The realistic long value is still caught by egress:jwt-token" was true and
hid the part that matters. Measured at the 257-char boundary: a generic long
password still trips entropy:base64-blob at CRITICAL, disposition unchanged.
A JWT used as a DB password is the case that moves -- its remaining detections
top out below CRITICAL, so the any-tier block is lost and PRESET_TRUSTED_SOURCE
drops from fail_secure to quarantine_review. PRESET_USER_UPLOAD still
fail_secures. Recorded as a behaviour change in the changelog, not buried.
The first probe for that boundary used a 300-char run of "A" and found nothing on
either version: all-same-char values are suppressed as placeholders. The probe was
wrong, not the pattern.
662 passed, coverage matrix exit 0, LIMITATIONS still 29 items = README's 29.
The output gate claimed LLM10 self-safety on the grounds that its patterns have
no nested quantifiers. True, and irrelevant: nesting is not what makes these
blow up. A run in front of a REQUIRED literal, reachable from a short anchor, is
enough -- crafted input repeats the anchor and never supplies the literal, so
every start position rescans the tail. Quadratic, not exponential, and the
max_scan_chars cap does not help: it bounds the input, and quadratic work on a
bounded input is still hours.
Measured, not argued. `<a:` x 100_000 took 23.4s in AUTOLINK_RE alone; the
composed gate on that payload took 458.7s, extrapolating to ~5.7 hours at the
1_000_000-char input the gate itself accepts. Size-matched ordinary prose runs
0.31s, so the separation is 18x-660x -- unlike the blob in the neighbouring
test, which is the *faster* side of prose and never exercised backtracking.
Two fixes, chosen per pattern rather than uniformly:
- active_content + lexicon JSON (15 runs): exclude the character that opens the
pattern's own anchor (`[` for markdown, `<` for tags), so a run cannot reach
past the next start position and the per-start costs telescope. Verified to
cost no recall: long URLs, long alt text, and `<` inside a quoted attribute
all still match. Bounding instead would have been linear too but wrong here --
the content is attacker-controlled, so padding past a bound would be a
one-line bypass of the EchoLeak class this table exists to catch.
- connstr egress (4 runs): bound the password at MAX_CONNSTR_VALUE. The
exclusion fix is unavailable -- the anchor character is `/` and passwords
containing `/` are the common case (measured: they match today). The residual
miss is a credential over 256 chars; a token that long is still caught by
egress:jwt-token.
hybrid-xss:script-tag had neither option: its run is the script BODY, which may
legitimately contain `<`. It now matches the opening tag and drops the
`</script>` requirement. That also closes a fail-open -- `<script>alert(1)`
unclosed was silently missed -- at the cost of flagging prose that merely
mentions `<script>`, now documented.
Found by the composed-gate test staying red after every individual scanner was
already linear: the lexicon's six html-obfuscation patterns were the remaining
813x. A per-scanner test alone would have shipped that.
662 passed (was 642), and faster than before the fix.
v0.3.0 made the untrusted upload path unusable: measured on both doors, an
ordinary remote image fail_secure'd and an ordinary link/autolink/refdef
quarantined, so only documents without external references persisted.
Two independent defects compounded; neither fix works alone:
1. `markdown-image: HIGH` fired on any external image. The exfil primitive is a
URL that moves bytes outward, not an image. `is_ordinary_url` now grades on
shape - http(s)/protocol-relative, no query, no userinfo, no percent-escape,
no opaque host label or path segment -> LOW; anything data-carrying keeps the
carrier's severity. raw-html and data: URIs stay HIGH unconditionally.
Opacity reuses entropy's primitives; floors calibrated against real doc URLs
(worst legit token H=4.08, exfil segments 4.36-4.54) and frozen in
calibration.
2. The quarantine_default floor fired on ANY finding, a premise that broke when
every ordinary link became a finding. It now fires at MEDIUM+ - a no-op for
every detector that shipped before 0.3.0 (no LOW/INFO exists), which is what
makes this a patch rather than a minor.
The corpus blind spot that let this pass 522 green tests is closed: the FP
corpus carries realistic markdown and is asserted on the OUTPUT gate under
PRESET_USER_UPLOAD, with a counter-corpus of exfil-shaped URLs that must still
block. Beaconing and short opaque segments are conceded in LIMITATIONS and
asserted by the coverage matrix rather than papered over.
No new public API; no new preset (0.4.0 work); allow_reserved default unchanged.
Version-sync across pyproject, __init__, README badge/status/install pin and
CHANGELOG, and cut [Unreleased] to [0.3.0].
Why minor: 0772daf made allow_reserved default to True on okf.import_bundle,
so a consumer who upgrades without touching their code gets a LOOSENED gate --
a reserved index.md/log.md in a received bundle is now scanned and may become
mergeable, where v0.2.0 rejected it unconditionally. Under 0.x a >=0.2,<0.3
pin absorbs a 0.2.1 silently but stops at 0.3.0, which is the signal such a
change should send. Found by llm-ingestion-okf, our first real downstream
consumer, against main.
Development Status stays 3 - Alpha and the README keeps "the public API may
still change": this ships the hardened surface (Sessions A/A2/B) to consumers
who are still pinned at v0.2.0 and therefore have none of it. It is not the
v1.0 freeze -- that stays gated on the first real integration coming back
green, which is exactly what 0.3.0 makes possible.
Verified: 522 passed; coverage matrix exit 0; version string present in all
four files; no dangling 0.2.0 outside CHANGELOG history.
Add a single declarative manifest proving, in one place, every vulnerability
class the guard stops — and the documented gaps it does not. This is the
real-case validation gate ahead of any v1.0 freeze (v1.0 stays parked until
verified on real cases).
- src/llm_ingestion_guard/coverage.py: stdlib-only manifest (CORE_CASES) +
narrated runner. `python -m llm_ingestion_guard.coverage` prints
class -> OWASP -> expected -> observed -> verdict; exit 0 iff every caught
class is caught and every documented gap holds. 126 caught classes + 4 gaps.
Lexicon cases are generated from load_lexicon() via a payload dict, so a
pattern with no payload fails loudly at import (self-verifying).
- tests/test_coverage_matrix.py: asserts total recall, that every documented
gap still holds, and completeness (every lexicon id + every OWASP anchor has
a case). Adds the full 25-pattern LLM02 secret-egress set (fixtures assembled
from split tokens so no secret shape sits in source) and the container-layer
front-end classes (CSV formula-injection, zip-slip, zip-bomb, symlink).
- README + CHANGELOG: point to the runnable matrix.
+165 tests (357 -> 522). No core dependency added.
Session D: move every calibration constant (entropy floors 5.4/128, 5.1/64,
4.7/40 + shape floors; MAX_SCAN_CHARS; rot13-min; cognitive-load lengths
2000/2500; disposition ranks; active-content severities) into one documented
calibration.py, so a parallel Node/TS port can mirror exactly the same numbers.
Pure refactor, zero behavior change: calibration is a leaf module (imports only
report.Severity) that entropy/lexicon/disposition/active_content now source
their thresholds from. MAX_SCAN_CHARS is re-exported from lexicon so output.py
and existing callers are unaffected. The 347 pre-existing tests pass unmodified;
new test_calibration.py freezes the values and asserts each detector actually
reads its threshold from calibration (identity-checked, not a dead copy).
Output gate step 3 now runs scan_secret_egress over every decoded base64
blob's plaintext, not only scan_lexicon. A base64-wrapped credential that
formerly vanished (decode fed the lexicon, which has no secret patterns)
now surfaces as decoded:egress:* carrying the blob offset. Evidence stays
length-only, so the decoded finding never leaks the secret value.
Hex-wrapped secrets remain a documented honest-limit (entropy exposes
decoded plaintext for base64 only). README honest-limits + CLAUDE.md
Kontekst updated; 3 tests added (347 passed, was 344).
A received OKF bundle MAY legitimately carry index.md (directory listing, read
first under progressive disclosure) and log.md (update history) at any level
(spec §3.1/§6/§7). import_bundle previously hard-rejected those basenames in the
T4 path gate, so a conformant third-party bundle was over-blocked in full
(FAIL_SECURE) — and because the reject fired before scan_concept, index.md's
body (the highest-priority injection surface) was never scanned.
import_bundle now defaults allow_reserved=True: reserved basenames are scanned
as structural files (path-safety checks — traversal / absolute / backslash / .md
— still apply). The shadow-reject (an *upload* masquerading as index.md) is
preserved: the front-end passes allow_reserved=False so a materialized upload
landing on a reserved basename is still refused. That front-end opt-in was
required to keep the shadow-reject once the default flipped (not in the plan's
Filer set; traced from the code).
- okf.py: validate_concept_path/_validate_concept/import_bundle gain the
keyword; validate_concept_path default stays False (strict standalone).
- tests: +3 (legit index/log admit; injection in index.md body caught;
okf_version frontmatter admits). Per-concept-iteration test switched to a
traversal vector; mode-b showcase's index.md surface reframed from
reserved-name-reject to index.md-body-scan.
- README honest-limits + CLAUDE.md context note the mode-b/upload distinction.
Suite: 341 -> 344 passed. Core invariant intact (dependencies=[]).
Close the EchoLeak wiring hole (CVE-2025-32711 class): markdown images/
links, reference definitions, autolinks, raw active HTML and data: URIs
now surface as report-only findings (active:*, OWASP LLM05) in
scan_output step 6, so screen_output and okf.import_bundle dispose of
them instead of admitting them with findings=[].
- new active_content.py: canonical home of the shared pattern table +
scan_active_content; neutralize refactored to import it (mutating API
and behavior unchanged, all neutralize tests pass as-is)
- images/links flagged only for absolute/protocol-relative URLs:
relative in-bundle links are legitimate wiki/OKF mechanism (principle 5)
- evidence carries defanged URLs only (hxxps://evil[.]example)
- EchoLeak vectors planted in both showcases; detach proofs cover them
- README export list + checklist step 6, CLAUDE.md context line updated
Suite: 321 -> 341 passed. Core invariant intact (dependencies=[]).
Pre-release hardening from an independent adversarial review; each fixed
test-first (failing test -> fix -> green). 214 tests pass.
- entropy (M1): decode-and-rescan now runs BEFORE false-positive suppression,
so an SRI/media-prefixed injection blob is still decoded and lexicon-rescanned.
Suppression gates only the entropy finding, never the decode.
- output/disposition (M3): the invisible-carrier invariant now holds on the
persist gate. scan_output flags zero-width/BIDI presence and disposition
treats those + lexicon:unicode-tags-present as any-tier carriers, so a carrier
in model output fails secure even under a trusted policy.
- contract (M2): assert_credential_allowlist catches a bare <PROVIDER>_KEY
(e.g. STRIPE_KEY) that the old regex silently missed (fail-open). Deliberately
broad: also flags PARTITION_KEY/SORT_KEY as loud, allowlistable FPs -- fail-loud
beats fail-silent for an isolation control.
- disposition (m6): guard runs decide inside its guarded block -> total
fail-closed even on a malformed report.
- output (m4): egress placeholder suppression anchors word markers (example,
todo, ...) to a word boundary, closing a fail-open where a real secret merely
containing such a word was suppressed.
Docs: CHANGELOG Security subsection; README honest-limit for lexicon dedup (m5,
documented tradeoff, not fixed).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HyRCQMocjZ6SmSQ6JidJ2k
Module 11 (final) — the top-level wiring. The library never makes the model call
(no SDK imported by the core), so the public surface is the toolkit plus two
library-side bookends around the caller's tool-less transform (Form 1, chosen
with the operator over an export-only toolkit and a full orchestrator — the
bookends fit existing pipelines with least friction, encode the two halves the
library can stand for, and impose no control flow):
- prepare_input(text, source=INPUT) -> PreparedInput(fenced, nonce, report):
§6 steps 1-2, sanitize THEN fence (carrier can never smuggle a forged
delimiter). Merged report carries both steps' findings; renders no disposition.
- screen_output(text, policy, *, provenance, transform_failed) -> DispositionResult:
§6 steps 6-7, scan_output under guard() so a scanner error fails CLOSED
(FAIL_SECURE, never a silent persist). transform_failed routes the compound
forced-fallback rule.
- __all__ exports the full framework-agnostic surface: detectors, result types,
disposition machinery + presets, contract asserters, the grounding seam.
Docs: README refreshed from the stale "brief / pre-implementation" line to a v0.1
alpha status with a Form-1 quickstart, the §6 adopt-this checklist, and an honest
-limitations section (structural unsolvability at the text layer; semantic
poisoning invisible to lexicon+entropy; text-only, no multimodal). CHANGELOG
seeded; CLAUDE.md remote/status lines corrected (remote IS set, no longer
brief-stage).
10 wiring tests (public surface, prepare_input compose, screen_output fail-closed
+ compound). 189 green (showcase + corpora follow).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HyRCQMocjZ6SmSQ6JidJ2k
Module 10 of the build order — interface only in the stdlib core (PLAN §67/§94,
BRIEF §7/§10). lexicon and entropy see surface signals; they are structurally
blind to semantic poisoning — a factually false or subtly biased claim, in clean
prose, carrying no suspicious token. Catching that needs grounding against a
source of truth (embedding classifier, retrieval check, LLM judge) — a model
call, and models never live in this core.
So this module ships exactly two things and no detector logic:
- SourceGroundingCheck: the text -> Report protocol a [judge] implementation
must satisfy to plug in. runtime_checkable for a coarse callable-vs-not
isinstance gate; a conforming impl may be a plain function or a stateful
callable holding a retriever/client — the grounding source of truth is the
impl's concern, never a seam parameter. Its findings flow through disposition
like any other detector's, with zero grounding-specific plumbing.
- no_grounding_check (bound as DEFAULT_GROUNDING_CHECK): the pass-through
default returning an empty Report. The honest scope note made structural —
semantic poisoning is not solved at the text layer, and the core does not
pretend to.
Design choice, tested: the default returns NO finding (not an INFO "unchecked"
marker). An INFO finding would flip every artifact to found and trip the
quarantine_default floor in disposition, quarantining every upload for a check
that never ran. The seam stays silent; the honesty lives in the contract.
8 new tests (pass-through empties, silence on semantic poison, protocol
conformance incl. a stateful judge stub, and a composition test proving a
plugged-in check's HIGH finding fails secure through disposition unchanged);
169 green total.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HyRCQMocjZ6SmSQ6JidJ2k
Module 9 of the build order — the differentiator. Where the other modules
detect and report, these are pure functions that ENFORCE an invariant and
raise: the write-time analogue of runtime least-privilege. They harden the
call a pipeline makes around its quarantined transform; the library makes no
model call itself.
Three asserts, matching the reusable-contract checklist (BRIEF §6 steps 3-4):
- assert_tool_less(request): the model request carries no tool surface —
tools/functions/tool_choice/function_call/mcp_servers, populated. Covers
both Anthropic and OpenAI request shapes; empty/None is genuinely tool-less.
- assert_credential_allowlist(env, allowed): the process env holds no
credential beyond this stage's allowlist (subset = least-privilege; the
enrichment stage sees only the model key, never the publish credential).
- scoped_env(env, allowed): the isolation primitive — strips off-allowlist
credentials, keeps PATH etc.; the assert then passes by construction.
Generalized from claude-code-llm-wiki tools/wiki_ingest/enrich.py
assert_quarantine (a pipeline-specific gate) into framework-agnostic pieces.
Two deliberate safety choices inherited from the reference: credential
detection is name-based (env VALUES are never read — value-scanning is the
output module's job); and a raised ContractViolation names only the offending
KEY, never a value, so it is safe to route to an alert channel (minimal-alert,
BRIEF §6 step 8). CREDENTIAL_NAME_RE ported verbatim from the proven reference.
23 new tests; 161 green total.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HyRCQMocjZ6SmSQ6JidJ2k
Module 7 of the build order: the last gate before model output is persisted.
Composes scan_lexicon + scan_entropy over the emitted text, feeds each base64
blob entropy decoded back through the lexicon (decode-and-rescan → decoded:*
findings with blob offset), and adds the LLM02 secret/credential egress layer
(cloud/provider keys, PEM headers, DB conn-strings, JWT, labelled
password/secret/api-key assignments) with placeholder/varref FP-suppression.
Report-only (never mutates; neutralize is the separate opt-in mutator). Evidence
carries only a description + match length — never the secret value. Self-safe:
single input-size cap, linear egress patterns. PEM patterns use -{5} form so the
module itself never trips a secret scanner. 26 new tests; 108 green total.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HyRCQMocjZ6SmSQ6JidJ2k
Build-order step 6. Close the EchoLeak class (CVE-2025-32711): active content in
persisted model OUTPUT that a downstream renderer auto-fetches or makes clickable,
exfiltrating data zero-click. These carriers are neither injection strings nor
high-entropy, so lexicon + entropy miss them — a distinct control (OWASP LLM05,
Improper Output Handling).
Defang, don't delete. URLs in active-content position are rewritten to a
non-resolvable but auditable form (https://evil.com -> hxxps://evil[.]com;
data:/javascript: colon neutralized to [:]); raw active HTML is escaped so a
renderer shows inert literal text. Visible information survives review; only the
machine-actionable affordance dies. Dot-defang is idempotent (never [[.]]).
Six classes, each a Finding: markdown-image (HIGH, the zero-click primitive),
inline-link (MEDIUM), reference-link definition (MEDIUM, the documented
image-filter bypass), angle-bracket autolink (MEDIUM), raw active HTML (HIGH,
inherently-active tag OR event/URL attribute — benign <b>/<em> left untouched),
standalone data: URI (HIGH). Processing order prevents double-counting.
Opt-in and separate: calling neutralize() IS the opt-in to mutate; the report-only
gate stays pure (design principles 3 & 4). Byte-identical on clean output, mirror
of the sanitizer invariant. Scope conceded in the docstring: a targeted defanger,
not a full HTML sanitizer.
17 tests: byte-identity + FP guards (lone <>[], metadata:, benign HTML), image
defang + non-resolvability, secret-exfil URL, inline/reference/autolink, raw-html
escape + script neutralization, data: URI, no double-count, counts, source.
[skip-docs]: README positioning + honest-limitations remains the deliberate
build-order step-11 deliverable (steps 1-5 likewise left README frozen).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HyRCQMocjZ6SmSQ6JidJ2k
Build-order step 5. Wrap untrusted content in a quarantine fence a downstream
trusted prompt can rely on: everything between the delimiters is data, never
instructions.
Two load-bearing properties:
- Per-call cryptographic nonce (secrets.token_hex, 128-bit) in the delimiter, so
an attacker embedded in the payload cannot forge the matching closing marker to
break out — the nonce is unpredictable and fresh every call.
- Marker-strip FIRST: fabricated fence markers already in the payload are removed
(any/no nonce, case-insensitive, ReDoS-safe negated-class regex) and flagged as
fence:marker-injection (HIGH, LLM01) before wrapping — defense in depth against
a lucky guess of the static skeleton, and it surfaces the attempt.
Pure text -> (fenced_text, report, nonce); only mutation is the marker-strip.
Nonce exposed so the caller can reference the fence in the trusted prompt.
10 tests: wrap/preserve, per-call randomness, nonce length, breakout containment,
marker-strip (+ case-insensitive), prose-word FP guard, source, empty input.
[skip-docs]: README positioning + honest-limitations is a deliberate build-order
step-11 deliverable (steps 1-4 likewise left README frozen). README status line
("pre-implementation") is stale and flagged for the step-11 refresh.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01K8GmKRCdsPjWYAKWsNgeQS
Build order step 4 — the load-bearing port from the llm-security seed
(injection-patterns.mjs + string-utils.mjs), stdlib-only.
- injection_lexicon.json: 83 patterns (CRITICAL/HIGH/HYBRID/MEDIUM) as the
single source of truth (regex + id + severity + owasp + desc), compiled once
by a thin loader. Decoupled from the engine for a future TS port.
- scan_lexicon(text, source, max_scan_chars) -> Report: matches every pattern
against a deduped variant set (raw / normalized / homoglyph-folded / rot13),
plus unicode-tag presence signal and the cognitive-load trap.
- normalize_for_scan chain ported: unicode-tags -> bidi -> HTML-entities ->
unicode/hex/URL escapes -> whole-string base64 (reuses entropy.try_decode_base64)
-> collapse letter-spacing; plus fold_homoglyphs / rot13.
- Self-safety (OWASP LLM10): input-size cap (scan prefix + flag oversize) and
ReDoS-safe port — the two nested-.*? sub-agent patterns bounded to
(?:\S+\s+){0,N}?; verified true positives still fire.
- Non-Latin data (homoglyph map, BIDI block) built from explicit code points;
JSON non-ASCII kept as \uXXXX escapes.
24 tests; 55 green total.
[skip-docs]: README positioning + honest-limitations is a deliberate build-order
step-11 deliverable (steps 1-3 likewise left README frozen). README status line
("pre-implementation") is stale and flagged for the step-11 refresh.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01K8GmKRCdsPjWYAKWsNgeQS
Build order step 3. Pure text -> findings detector ported from the
llm-security entropy-scanner seed:
- Length-calibrated Shannon-entropy classification (CRITICAL 5.4/128,
HIGH 5.1/64, MEDIUM 4.7/40).
- Shape floor: base64-like (len>100) / hex (len>64) reach at least MEDIUM
even when entropy alone does not trigger — the only path that catches hex
(16-symbol alphabet caps H at 4.0 < 4.7).
- Decode-and-rescan (must-have): base64 blobs that decode to printable text
are exposed on EntropyResult.decoded for a later lexicon rescan.
- FP suppression scoped to the text-relevant subset (base64 media data-URI
prefixes + SRI sha*- prefix); source-code-specific seed rules omitted.
Exposes ported primitives shannon_entropy / is_base64_like / is_hex_blob /
try_decode_base64. 16 new tests; full suite 31 green. Stdlib-only.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01K8GmKRCdsPjWYAKWsNgeQS
