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 query GitHub (via gh) and "Read the full issue: body, all comments" and use that user-generated issue/comment content to decide state transitions and post labels/comments, which exposes the agent to untrusted third-party content from GitHub issues.