github-triage
Warn
Audited by Snyk on Mar 3, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's PHASE 1 explicitly fetches open issues and PRs via the gh CLI (gh issue list / gh pr list), and the SUBAGENT_PROMPT templates require reading issue/PR bodies and comments (user-generated, untrusted content) to decide actions like commenting, closing, or merging, so third-party content can directly influence agent actions.
Audit Metadata