defect-lifecycle-agent-skill

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime chain ingests the user’s defect source-of-truth (e.g., tracker ticket / user report text) into the agent context via the “source-of-truth artifact” and subsequent report-generation steps, and that defect text is outsider-authored when it comes from issues/support messages/comments not written by the operating user.