issue-triage

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

• Third-party content exposure detected (high risk: 0.90). Step 1 of SKILL.md explicitly requires fetching GitHub issue content (user-generated public third-party content) via gh issue view or WebFetch, and the agent must read and act on that content to diagnose, decide, and post comments—allowing untrusted content to materially influence tool use and next actions.