open/llm-ingestion-pipeline-security
1
0
Fork 0
Code Issues Pull requests Releases Activity
llm-ingestion-pipeline-secu.../CLAUDE.md
Kjell Tore Guttormsen b505f70485 docs: design brief for reusable LLM ingestion-pipeline security library 
Brief-stage repo. docs/BRIEF.md defines a minimal, framework-agnostic
library that packages the write-time ingestion contract (sanitize ->
fence -> tool-less quarantined transform -> per-stage capability
isolation -> scan output before persist -> fail-secure) as reusable
code. Positioned honestly against query-time guardrails (LLM Guard,
NeMo, Rebuff, Vigil) with a prior-art verification log. Reference
implementation: claude-code-llm-wiki Stage B.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HPAmFyEVWbwvmSNVdXTu4d
2026-07-04 06:18:32 +02:00

950 B
Raw Blame History

llm-ingestion-pipeline-security

Kontekst

Gjenbrukbar, minimal defensiv layer for LLM ingestion-pipelines (write-time), til forskjell fra query-time chatbot-guardrails. Pakker det arkitektoniske kontraktet — sanitize → fence → tool-less karantenert transform → per-stadium capability-isolasjon → scan output før commit → fail-secure — som komponerbar, framework-agnostisk kode.

Referanse-implementasjon: claude-code-llm-wiki Stage B (tools/wiki_ingest/). Lexikon-seed: injection-patterns.mjs fra llm-security-pluginen.

Repoet er på brief-stadiet. Start med docs/BRIEF.md.

Konvensjoner

  • Norsk for dialog og planer, engelsk for kode og innhold (repoet er ment publisert).
  • Ingen GitHub — kun Forgejo (git.fromaitochitta.com) hvis/når publisert.
  • Ingen remote satt ennå; ingen push før operatøren bestemmer publisering.
  • Minimal-dependency: stdlib-first kjerne; ML/judge-detektorer bak extras.