alert-triage

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

• Third-party content exposure detected (medium risk: 0.65). SKILL.md’s required workflow explicitly includes ingesting the “raw event(s) that triggered the alert” (which can contain outsider-authored free text such as log lines/messages from third-party systems or other authors) into the agent context via the “Alert data”/“Alert payload” data-collection path.