open/llm-ingestion-pipeline-security
1
0
Fork 0
Code Issues Pull requests Releases Activity
Reusable, minimal, dependency-light defensive layer for LLM ingestion (write-time) pipelines — sanitize, fence, tool-less quarantined transform, capability isolation, output-scan-before-persist, fail-secure.
2 commits 1 branch 2 tags 992 KiB
  • Python 100%
Find a file
Kjell Tore Guttormsen 41473d9db2 docs(brief): add MS AI Security plugin as second consumer; source-trust disposition 
Second target consumer named: MS AI Security plugin, an ingestion
pipeline over Microsoft Learn content that includes user-generated Q&A
(learn.microsoft.com/answers, plus ingested MSDN/Stack Overflow). This
is the high-untrust case where the contract is load-bearing, not
hygiene. New design principle 4.7: disposition scales with source trust
(pinned changelog = WARN; open UGC = quarantine/hard-fail on high
severity). Day-1 rationale: architectural controls are cheap to design
in, expensive to retrofit (consumer 1 is proving that at its A13).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HPAmFyEVWbwvmSNVdXTu4d
2026-07-04 06:26:55 +02:00
docs docs(brief): add MS AI Security plugin as second consumer; source-trust disposition 2026-07-04 06:26:55 +02:00
CLAUDE.md docs: design brief for reusable LLM ingestion-pipeline security library 2026-07-04 06:18:32 +02:00
README.md docs: design brief for reusable LLM ingestion-pipeline security library 2026-07-04 06:18:32 +02:00

README.md

llm-ingestion-pipeline-security

A reusable, minimal, dependency-light defensive layer for LLM ingestion pipelines — the write-time siblings of query-time chatbot guardrails.

Where mature guardrails (LLM Guard, NeMo Guardrails, Rebuff, Vigil, …) sit between a user and a model at query time, this library hardens the other shape: untrusted content flowing through an LLM enrichment/summarization/extraction step into a persisted, downstream-consumed artifact (RAG corpus, knowledge base, wiki). It packages the architectural contract — sanitize → fence → tool-less quarantined transform → per-stage capability isolation → scan output before commit → fail-secure — as composable, framework-agnostic code.

Status: brief / pre-implementation. Start with the design brief:

The contract is extracted from a working reference implementation (the claude-code-llm-wiki Stage B enrichment pipeline).