concept-synthesis

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

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 3 explicitly instructs the agent to "read the timeline + associated source pages" and related docs note that concept stubs come from ingesting "links / articles" (idea-ingest), meaning the agent consumes untrusted public/third‑party content and uses it to drive tiering and LLM synthesis decisions.