Order 20260902T150716Z from .claude -- a K5 blocker in the OKF programme.
`parse_frontmatter` rejected `sources` in every form the spec and its
producers actually use. Measured 02.09 by two consumers independently:
`sources: [{ id: a, resource: x }]` raised on the `[` indicator (one entry
as well as two), and the block sequence of block mappings -- SPEC.md 5.1's
OWN example -- raised "nested mappings are not supported". `resource` is
REQUIRED within a `sources` entry, so the whole provenance family was
unwritable and a bundle written the way the spec documents it was refused.
Measured against the spec before coding, not reasoned: 5.1's example block
is the canonical carrier for a REQUIRED field and 11.1 defines conformance
as parseable frontmatter, so refusing it refuses a conformant bundle. Both
carriers now parse to the same list of dicts.
The load-bearing change is not the carrier, it is WHO admits `resource`.
1.2.0 left it off the allowlist arguing the parser could not tell
`sources[].resource` (5.1, a citation) from `executor.resource` /
`attester.resource` (10, a pointer to code to be run -- the door-C route
closed in 1.1.0). That premise was false: the owning key is in scope at
every call site and was simply never threaded through. It is threaded now,
so the discrimination is structural, and door C stays shut through EVERY
carrier including the two this adds -- pinned by a new test that drives
`executor`/`attester` through all four.
Refusal stays the default elsewhere. A flow sequence of plain scalars
(`tags: [a, b]`) still raises: the sequence carrier is opened for the flow
mapping element and nothing else. A `sources` entry admits scalar leaves
only, so 5.1's optional PER-ENTRY `usage_window` is refused -- no nesting
past depth 1 is a security property and it was not spent here; registered
as a conformance gap rather than left as an oversight. A block list may not
mix scalars and mappings, because a consumer reading `entry.get("id")` over
one gets an AttributeError off the first str.
New residual registered: `sources[].resource` is scanned as text (T1) but
never URL-validated. T3's https allowlist cannot reach it without
over-blocking conformant bundles -- 5.1 permits bundle-relative paths and
scope descriptors, and the producers' own golden emits `resource: fixture`.
A consumer that dereferences it must call `validate_resource_url` itself.
Suite 834 -> 859 green. 25 new rows; four pre-existing rows changed because
this release changed the behaviour they pinned, two of them renamed since
their names asserted the old invariant (`exactly_one_route_to_a_mapping`,
`two_keys_per_item_is_where_the_block_list_hard_rejects`). Not "unchanged".
130/130 classes, 6/6 gaps hold, 44 -> 45 limitations, ReDoS 0/152 (the
sweep adds no evidence here -- this change adds no regex and the splitting
is linear). Six version surfaces bumped by hand, no sed. Re-measured alone
after the bump.
No exported surface changed; no detector behaviour and no calibration
changed.
4.5 KiB
llm-ingestion-pipeline-security
Kontekst
Gjenbrukbar, minimal defensiv layer for LLM ingestion-pipelines (write-time), til forskjell fra query-time chatbot-guardrails. Pakker det arkitektoniske kontraktet — sanitize → fence → tool-less karantenert transform → per-stadium capability-isolasjon → scan output før commit → fail-secure — som komponerbar, framework-agnostisk kode.
Referanse-implementasjon: claude-code-llm-wiki Stage B (tools/wiki_ingest/).
Lexikon-seed: injection-patterns.mjs fra llm-security-pluginen.
Repoet er på v1.3.0 — den eksporterte Python-surfacen er frosset under semver
(deteksjonsatferd er det IKKE; kalibrering flytter seg i 1.x). Stdlib-kjernen er
bygget og testet (15 moduler +
topp-nivå wiring, showcase + korpus), inkl. OKF-adapter og aktivt-innhold-
detektor (EchoLeak-klassen) i output-gaten. OKF-frontmatterens mapping-klasse
har fire uttrykkbare bærere (G3 21.08, G30 02.09): flow-mapping som verdi
og som blokkliste-element, flow-sekvens av flow-mappinger, og blokk-sekvens av
blokk-mappinger (SPEC §5.1s egen form). HVER nøkkel i alle fire står på
allowlisten og hvert blad er en ren skalar. Formen er trygg fordi allowlisten
inspiserer hver nøkkel; det blanke avslaget var håndhevelsen, ikke poenget.
resource er allowlistet KUN inne i en sources-oppføring — foreldre-
nøkkelen avgjør, så executor/attester sin resource (§10, dør C) avvises
gjennom hver eneste bærer. 1.2.0s begrunnelse for å utelate den (parseren
manglet foreldre-kontekst) var målt feil: konteksten var der, den var bare
aldri tredd gjennom. Topp-nivå blokk-mapping, dotted- og inline-kolon-rutene
raiser fortsatt, flow-sekvens av rene skalarer (tags: [a, b]) raiser, en
blokkliste kan ikke blande skalarer og mappinger, og en avvist mapping raiser —
den degraderer aldri til en streng (1.1.0-defekten). sources[].resource
URL-valideres ALDRI (T3 ser kun topp-nivå resource) — §5.1 tillater
bundle-relative stier og scope-beskrivelser, så en https-gate ville over-blokkert
konforme bundles; konsumenten må selv kalle validate_resource_url. Mode-b import_bundle skanner
reserverte strukturfiler (index.md/log.md) i mottatte bundles i stedet for å
path-avvise dem; upload-front-end beholder shadow-reject (allow_reserved=False).
Output-gatens decode-and-rescan mater dekodet base64-klartekst gjennom BÅDE lexicon
og secret-egress (LLM02), så en base64-innpakket credential fanges som
decoded:egress:* i stedet for å forsvinne; hex-innpakket er en dokumentert
restgap (entropy eksponerer kun base64-klartekst). active:raw-html krever et
EKSTERNT mål på URL-attributt-grenen, og <base> er ute av det aktive navnesettet;
scanner og mutator har hver sin predikat (is_active_tag / is_defangable_tag).
Rå HTML graderes nå også på BÆRER: <a>/<area> er klikk-krevende og rapporteres
som active:raw-html-link (MEDIUM), og en tagg hvis hele affordans ER en URL den
ikke bærer (</a>, <Frame>, <video />) er inert. Klassifisering skjer i
active_tag_class; is_active_tag er en tynn wrapper, og census patcher den
FØRSTE (en boolsk patch kan ikke uttrykke en regradering).
ZWJ (U+200D) dømmes på KONTEKST, ikke identitet — unntas kun mellom to emoji, på
begge flater (sanitize eier predikatet, output importerer det).
Start med docs/BRIEF.md for design, README.md for bruk, docs/PLAN.md for
byggerekkefølgen.
Konvensjoner
- Norsk for dialog og planer, engelsk for kode og innhold (repoet er publisert).
- Ingen GitHub — kun Forgejo (
git.fromaitochitta.com). - Remote satt: offentlig
open/-speil på Forgejo; push hver commit (durabelt autorisert). - Minimal-dependency: stdlib-first kjerne; ML/judge-detektorer bak extras.
Communication patterns
Linking to local files
When pointing to local files in responses, always use markdown link syntax with a descriptive name:
- Use
[Human-friendly name](file:///absolute/path)— never barefile:///...URLs or autolinks<file://...>. - Always use absolute paths. Never
~/or relative paths. - For multiple files, render as a bullet list of named markdown links.
Why: bare file:// URLs only render the first as clickable across multiple lines. Named markdown links make each entry independently clickable and look cleaner.
Example (the path is a placeholder — the checkout root is the reader's own, and this file is published, so it must not carry one machine's directory layout):