github-triage

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and read full GitHub issue bodies and all comments (SKILL.md "Step 1: Gather context") using GitHub via the gh tool, and it uses that untrusted, user-generated content to drive triage decisions and produce agent briefs, which could allow indirect prompt injection.