triage

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

• Third-party content exposure detected (high risk: 0.90). Yes — SKILL.md explicitly instructs the agent to "query the issue tracker" and to "Read the full issue (body, comments, labels, reporter, dates)" (Gather context), which exposes it to untrusted, user-generated GitHub issue content that can materially influence triage decisions and downstream agent actions.