open/llm-security-commons
1
0
Fork 0
Code Issues Releases 1 Activity

docs: measure the lexicon port divergence, correct the case count

Browse source 
The guard's coverage.py turned out to be readable from a session here — the
read boundary covers llm-security only. Counting it instead of estimating
corrected two published numbers and surfaced the real conformance blocker.

Counted, not estimated: CORE_CASES holds 134 cases (128 caught, 6 gap), not
the "126 classes + 4 gaps-must-hold" the extraction plan claimed. 105 are
convertible to static input/expected; 29 assert a runtime API surface this
repository does not own, and are named as out of scope rather than faked.

Measured while counting, and the reason the corpus is still blocked: the
commons lexicon and the guard's are two ports of one source file, and they
disagree. 83/83 patterns correspond, 64 byte-identical, 6 differ only by
escaping and are proven equivalent by string identity, and 13 behave
differently — with a witness input for each and misses in both directions.
Cause is two different ReDoS mitigations of the same table: the Node side
bounds the run ({0,256}), the guard excludes the anchor character ([^><]).
Each has a recall cost the other does not.

No data file changed. Behaviour preservation is a v0.1.0 invariant, so the
divergence is reported to the owning repositories, not fixed here. The 8
hybrid severities the guard's port assigns are deliberately NOT copied in —
a second-hand port is not the producing module.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FaYqid3mejFmd9ZHsiHgp3
This commit is contained in:
Kjell Tore Guttormsen 2026-08-09 21:40:26 +02:00
commit 22d3a78591
4 changed files with 193 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

139
docs/lexicon-port-divergence.md Normal file
View file

@ -0,0 +1,139 @@
# Lexicon port divergence — commons vs the Python guard
**Status: informative.** Nothing here is normative and nothing here changes a data file. It
records a measured disagreement between two ports of one source table, so the decision can be
taken where each table is tested. Under this repository's behaviour-preservation invariant,
a divergence found here is **reported, not fixed**.
Produced 2026-08-09. Every number below came from a command; the scripts live in the session
scratchpad rather than in this repository, because executable code here would breach the
charter. They are reproducible from the method column.
## What was compared
| Side | Artefact | Version |
| --- | --- | --- |
| commons | [`lexicon/injection-lexicon.json`](../lexicon/injection-lexicon.json) | file `version` as committed |
| guard | `llm-ingestion-pipeline-security` `src/llm_ingestion_guard/injection_lexicon.json` | lexicon `version` 1.0, repo v0.3.4, commit `0bf0729` |
Both are **ports of the same file**: `llm-security/scanners/lib/injection-patterns.mjs`. The
guard's JSON says so in its own `note` field — *"Injection lexicon ported from llm-security
injection-patterns.mjs. Single source of truth."* Commons extracted the same table from an
operator dump of that module.
That is what makes the comparison worth running. These are not two different detectors that
happen to overlap; they are two transcriptions of one table, and where they disagree, they
disagree about what the same source says.
## Result
| Measure | Method | Result |
| --- | --- | --- |
| Pattern count, both sides | count entries | 83 and 83 |
| Label correspondence | match commons `label` to guard `desc`, em-dash normalised to hyphen | **83/83** |
| Regex source byte-identical | string compare | **64/83** |
| Differing regex text | string compare | 19 |
| — of those, provably equivalent | unescape commons' JS-isms (`\/` → `/`, `\uXXXX` → literal) and compare for string identity | **6/6 identical** |
| — of those, behaviourally divergent | differential match-set comparison (offsets + matched text), targeted corpus per pattern family | **13**, each with a concrete witness input |
| Total input comparisons | count | 401 |
| Flags | compare declared flags | **0 differences** |
| Severity / family | commons family vs guard `severity` | **8 differences** (all `hybrid`) |
64 identical + 6 escaping-only + 13 divergent = 83.
The 6 escaping-only pairs are equivalent by **string identity after unescaping**, not merely
by absence of a counter-example: `<\/system>` vs `</system>`, `text\/html` vs `text/html`,
`(?:https?:\/\/…)` vs `(?:https?://…)`, `(?:~\/)?` vs `(?:~/)?`, and two `\uXXXX`-vs-literal
character classes. Commons writes code points as escapes by convention; the guard's `note`
records the same choice for non-ASCII.
## The 13, and which side misses what
Divergence is **not one-directional**. Each side has inputs the other's pattern does not match.
| Pattern | Direction | Witness input |
| --- | --- | --- |
| `html-obfuscation: display:none element with content` | commons misses; span differs | attribute run padded past 256 chars |
| `html-obfuscation: visibility:hidden element` | span only | `<div data-x="<" style="visibility:hidden">x</div>` |
| `html-obfuscation: off-screen positioned element` | span only | same shape, `position:absolute` |
| `html-obfuscation: zero font-size element` | span only | same shape, `font-size:0` |
| `html-obfuscation: zero opacity element` | span only | same shape, `opacity:0` |
| `html-obfuscation: zero-size overflow-hidden element` | span only | same shape, `height:0;overflow:hidden` |
| `html-obfuscation: injection in aria-label attribute` | **commons misses** | `<a aria-label="` + 300 × `a` + `ignore">x</a>` |
| `markdown: suspicious instruction in link-reference comment` | **guard misses** | `[//]: # (a (b) ignore)` |
| `markdown: injection payload in link anchor text` | **guard misses** | `[click ignore this](http://e.com/a(b))` |
| `sub-agent: spawn instruction with dangerous capability keywords` | **guard misses** | `create an agent that` + 20 filler words + `execute` |
| `sub-agent: delegation with safety bypass instruction` | **guard misses** | `delegate to a new agent` + 200 chars + `bypass` |
| `hybrid-xss: <script> tag in content (agent context XSS)` | **commons misses**; span differs | `<script>alert(1)` (unclosed), `<script src=x.js>` |
| `hybrid-xss: iframe with executable src (agent context XSS)` | **guard misses** | `<iframe data-x="<" src="javascript:alert(1)">` |
"Span only" means both sides produce a match on the same input but over different extents —
the guard's match starts at an interior `<`. Whether that matters depends on whether a
consumer reports offsets or evidence text; it does not change whether a finding is raised.
The commons-side misses were confirmed in a real JS engine (Node v25.8.2, `RegExp` built from
the committed JSON), not only in the Python harness used for the differential.
## Why they diverge: two different ReDoS mitigations of one table
This is not drift, and framing it as a bug in either repository would be wrong.
Both ports have been hardened against catastrophic backtracking, by **different strategies**:
- **The Node side bounds the run.** `[^"]{0,256}`, `[^>]{1,256}`. Cost: an attacker who pads
the attribute past 256 characters falls out of the pattern.
- **The guard excludes the anchor character.** `[^><]`, `[^\]\[]`, `[^)(]`. Cost: content that
legitimately contains that character stops matching.
The guard's campaign is documented in its own CHANGELOG (v0.3.2 and v0.3.4: *"exclude the
character that opens the pattern's own anchor"*, a sweep over *"150 patterns across 11
tables"*), including its measured recall cost — it names exactly the two exceptions this
comparison rediscovered: *"URLs containing a literal `(` inside a markdown link target and
comment bodies containing a literal `(` before the keyword."* The bounded `{0,12}` / `{0,120}`
sub-agent quantifiers produce misses that the guard's exception list does not mention.
Neither strategy is free, and neither is obviously right. That is the decision the two owning
repositories have to take, and it is not commons' to take for them.
## Severity: the 8 hybrid patterns
Commons records the `hybrid` family with `severity: null` and a note that the seed dump did
not supply it, so a consumer **MUST NOT** assume one. The guard's port assigns all eight
`high`.
**This has deliberately not been copied into commons.** The guard's port is a second-hand
transcription, not the producing module; adopting its value would convert a documented gap
into an unverified claim, which is the defect class this repository's changelog already
records twice. It is reported instead, as a strong hint that the Node source assigns `high`,
for `llm-security` to confirm from the module.
## What this does not show
- **Not that either runtime misses an attack.** All witness payloads were re-tested against
every pattern table commons holds (111 compiled rules: 83 lexicon, 28 from
`active-content.json` and `secret-egress.json`). All of them still produce a finding, via
`active-content: constructs.raw-html`. The divergence is in the **finding set** — which
labels are raised — not in whether anything is raised at all. That still matters, because a
finding set is exactly what a `conformance/expected.json` would encode.
- **Not that `llm-security` behaves as described here.** Only its extracted pattern table was
available. Whether the Node engine runs an active-content table that compensates cannot be
determined from this repository.
- **Not dump-to-module fidelity.** Every check above proves the two *ports* agree or disagree.
That either matches `injection-patterns.mjs` remains `llm-security`'s assertion,
reproducible only in a session with read access to it.
- **Not exhaustive.** The corpus is targeted per pattern family, 401 comparisons. Absence of a
witness proves nothing except for the 6 escaping-only pairs, which are settled by string
identity rather than by the corpus.
## Consequence for `conformance/`
An `expected.json` names findings. Naming a finding needs a stable id, and the two runtimes do
not have one: the same pattern is `override:ignore-previous` in the guard and
`override: ignore previous instructions` in the Node table. The guard's JSON happens to carry
both — `id` and `desc` — which is evidence that a commons-owned id is achievable rather than
speculative.
So the id question is a **prerequisite** for the corpus, not a parallel task: until commons
owns a pattern id both ports map to, no fixture can be written, including for the 64 patterns
that are byte-identical. And for the 13 divergent patterns a fixture cannot be authored at all
without first deciding whose recall cost is the contract.