AG-013: Memory/RAG Poisoning Risk

What this rule means

Agent has writable persistent state without integrity protections.

Why it matters

CORDON-MAS research: 92.4% of RAG poison attacks succeed without retrieval filtering.

How to fix it

Add retrieval-stage filtering, use hybrid retrieval, validate memory writes.

Detect it

pip install lucin
lucin scan .                  # all rules
lucin explain AG-013          # this rule, in your terminal

Findings carry a file:line and, where the rule supports it, a witness path showing the flow that triggered it. Precision and recall for the whole rule set, with the commands that regenerate them, are on the benchmarks page — and the gaps are on limits.

← All detection rules