booklib-mcp-guide

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow for the lookup tool (and related tools) can ingest outsider-authored free text at runtime because lookup “searches across post-training corrections, team knowledge, and expert skills” and returns “source citations,” which implies the agent reads retrieved external documents/snippets into its LLM context.