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

4 commits

Author SHA1 Message Date
Kjell Tore Guttormsen
ca26e117ea feat(inbox): .xlsx extraction — formula gate, hidden sheets, cell comments (stage 2h) 2026-07-07 07:41:00 +02:00
Kjell Tore Guttormsen
24e57ca10b feat(inbox): two-stage upload front-end — text formats (stage 2a) 
Realistic-upload showcase (PLAN §247), first slice. A stage-1 front-end reads
dropped files and materializes them into an OKF bundle {concept_path: text} +
provenance; receive() wires extract -> import_bundle -> verdict. This slice
covers .txt/.md (stdlib only); .zip/.csv/folder/.docx/.pptx follow.

- Front-end lives in tests/ (showcase/dev-scoped), core stays stdlib-only:
  dependencies=[] untouched; python-docx/python-pptx added to the [dev] extra
  (used from stage 2d/2e), never a public [extract] extra (not v1 per PLAN).
- .txt injection -> guard T1 -> REJECT; clean .txt -> ADMIT; a dropped .md keeps
  its frontmatter so a dangerous value -> T2 REJECT; an index.* upload
  materializes onto the reserved uploads/index.md -> T4 REJECT.
- Detach-proof: neuter extraction to an empty bundle -> the poisoned upload
  ADMITs, proving the verdict depends on extraction carrying the payload.

Tests 282 -> 288.
 2026-07-06 11:04:23 +02:00
Kjell Tore Guttormsen
542ac92349 release: v0.2.0 — OKF adapter (stream 1); version sync pyproject/__version__/badge/CHANGELOG 2026-07-06 09:45:53 +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