github-automation
Warn
Audited by Snyk on Feb 16, 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 performs actions that read and review GitHub pull requests, issues, and repository content (e.g., "npx claude-flow github review --pr 123" and issue listing/reading), which are untrusted, user-generated public content on GitHub and thus could introduce indirect prompt injection.
Audit Metadata