open/llm-ingestion-pipeline-security
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity Actions
48 commits 1 branch 2 tags 913 KiB
Commit graph

5 commits

Author SHA1 Message Date
Kjell Tore Guttormsen
896ab4034a docs(plan): showcase covers realistic upload formats — two-stage extract→guard, dev-scoped parsers, honest binary-layer limits 2026-07-06 10:18:43 +02:00
Kjell Tore Guttormsen
ba7fc68c05 docs(plan): re-sequence v0.2+ streams — defer consumer integration, add OKF inbox showcase as next build 
Ground-truth pass over the named flagship consumer (portfolio-optimiser's
'OKF-upload-inbox') found it does not exist as a seam: both optimiser siblings
are frozen at release, carry their own OKF layer, receive no external bundles,
and take no dependency on this guard. Defer consumer integration (stream 2)
until the guard is mature; mature it here first, Node-port-friendly. Next
concrete build is the in-repo OKF inbox showcase (mode-b import_bundle as a
receive/quarantine gate), spec'd under 'The OKF inbox showcase'.
 2026-07-06 10:12:50 +02:00
Kjell Tore Guttormsen
43368e9684 docs(plan): lock v0.2+ stream sequencing (OKF->consumers->Node) + dependency rationale 2026-07-06 07:30:09 +02:00
Kjell Tore Guttormsen
a55404460a docs(plan): add end-to-end showcase pipeline test as the final deliverable 
One realistic content sample carrying many vulnerabilities at once, run through
a mock ingestion pipeline (sanitize -> lexicon+entropy+decode-rescan -> output
gate -> disposition); assert every planted vuln is caught and disposition fails
secure. Doubles as the README worked example. Added to build-order step 11 and
the test strategy; tracked as task #11. Inspiration: llm-security/examples/*.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01K8GmKRCdsPjWYAKWsNgeQS
 2026-07-04 17:23:17 +02:00
Kjell Tore Guttormsen
a9c4ccd8c7 feat: scaffold package + report and sanitize modules (TDD) 
Build order steps 1-2 of docs/PLAN.md:
- pyproject.toml (llm-ingestion-guard, stdlib-only core, extras [ml]/[judge]/[dev]), LICENSE (MIT)
- report: Finding/Report/Severity/Source shared type (pure data)
- sanitize: carrier stripping (zero-width, BIDI, Unicode-tag, HTML comment,
  data: URI) with the byte-identical / removes-only invariant
- docs/PLAN.md: v1 implementation plan (positioning A, gap-expanded scope,
  llm-security reuse map)

15 tests passing.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01K8GmKRCdsPjWYAKWsNgeQS
 2026-07-04 09:24:20 +02:00