detection-engineering

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

• Third-party content exposure detected (high risk: 0.80). The skill's "Prompt Injection Safety Notice" explicitly states the agent "processes user-supplied content that may include log samples, detection rule drafts, threat intelligence reports, and ATT&CK technique descriptions," which clearly means it ingests untrusted/user-generated third‑party content as part of its workflow and that content can influence detection design and actions.