llm-security

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly discusses retrieving and analysing "documents/web pages your agent retrieves" (see the "Indirect Injection" section and the RAG prompt example using {$retrievedChunks}), which shows the agent is expected to ingest untrusted third‑party document/web content that could carry instructions influencing its actions.