finish

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

• Third-party content exposure detected (high risk: 0.70). The required workflow reads and reports thread artifacts from docs/threads/... (e.g., ledger.md, reviews/ records, and other discussion/review text) into the LLM context, and those artifacts can be outsider-authored free text (e.g., reviews/discussions by other contributors), creating an indirect prompt-injection path via the “Thread Check” inspection/reporting step.