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.
Find a file
Kjell Tore Guttormsen 39991bd251 chore: repo scaffolding via /repo-init
Add .gitignore (Python stack + obligatory lines; /STATE.md kept local-only
until a private remote exists), CHANGELOG.md, and the Communication patterns
section in CLAUDE.md. STATE.md is gitignored — must never reach the public
open/ mirror.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01K8GmKRCdsPjWYAKWsNgeQS
2026-07-04 08:39:23 +02:00
docs docs(brief): fold in ms-ai-architect Layer B learnings (first output-side impl) 2026-07-04 08:32:38 +02:00
.gitignore chore: repo scaffolding via /repo-init 2026-07-04 08:39:23 +02:00
CHANGELOG.md chore: repo scaffolding via /repo-init 2026-07-04 08:39:23 +02:00
CLAUDE.md chore: repo scaffolding via /repo-init 2026-07-04 08:39:23 +02:00
README.md docs: design brief for reusable LLM ingestion-pipeline security library 2026-07-04 06:18:32 +02:00

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).