security-threat-modeling

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

• Third-party content exposure detected (medium risk: 0.65). Required workflow includes “Review untrusted repository processing and sandboxing needs” and “runtime trace or repository-processing flows,” which at runtime can ingest outsider-authored free text such as issue/PR/wiki/discussion content or repository body text into the agent’s LLM context for threat modeling.