github-cleanup
Warn
Audited by Snyk on Feb 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses untrusted, user-generated GitHub content via the gh API/CLI (e.g., repos/GH_USER/REPO/contents/.github/workflows, repos/.../dependabot/alerts, repo source files and manifests) and then interprets those findings to triage and decide cleanup actions, so third-party content can materially influence tool use and next actions.
Audit Metadata