open/llm-ingestion-pipeline-security
1
0
Fork 0
Code Issues Releases 4 Activity

feat: scaffold package + report and sanitize modules (TDD)

Browse source 
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
This commit is contained in:
Kjell Tore Guttormsen 2026-07-04 09:24:20 +02:00
commit a9c4ccd8c7
8 changed files with 564 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

11
src/llm_ingestion_guard/__init__.py Normal file
View file

@ -0,0 +1,11 @@
"""llm-ingestion-guard — a write-time defensive layer for LLM ingestion pipelines.
Query-time guardrails guard the answer; this library guards the *artifact*. It
packages the ingestion-side security contract — sanitize -> fence -> tool-less
quarantined transform -> per-stage capability isolation -> scan output before
persist -> fail-secure — as composable, stdlib-first, framework-agnostic code.
The public API is wired up as modules land; see docs/PLAN.md for the build order.
"""
__version__ = "0.1.0"