Tag

rag

5 entries, including 2 patterns.

1. 13 Oct

   A decoy puzzle is a denial of wallet

   OverThink plants an ordinary-looking puzzle in a page a reasoning model will retrieve. The answer stays correct, the user notices nothing, and the model burns many times the reasoning tokens you are billed for.

   • Red Team
   • ai-security
   • denial-of-wallet
   • rag
   • threat-model
2. 11 Oct

   A retrieved chunk is not a trusted source

   RAG delegates judgment to retrieval, and retrieval answers with whoever sits nearest in vector space. An attacker who controls a single document controls the top-k that reaches the model — before any instruction is ever written down.

   • Red Team
   • ai-security
   • rag
   • poisoning
   • vector-db
   • prompt-injection
   • threat-model
3. Pattern11 Oct

   Retrieved Evidence Promotion Gate

   Keep source claims and embedded instructions out of application authority, even when the poisoned chunk wins retrieval.

   • rag
   • prompt-injection
   • authorization
   • Red Team
4. 10 Oct

   A retrieved chunk is not a data point

   RAG poisoning turns your own retriever into the injection vector. A chunk that ranks top-k for a benign query is data to the pipeline and instructions to the model — and nothing in the stack can tell the difference.

   • rag
   • prompt-injection
   • llm-security
   • Red Team
   • supply-chain
5. Pattern10 Oct

   Retrieved Context Action Boundary

   Treat every retrieved chunk as evidence with provenance, while reserving tool and policy authority for a separate application-controlled gate.

   • rag
   • prompt-injection
   • llm-security
   • Red Team
   • authorization