research
Warn
Audited by Snyk on Feb 15, 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 ingests public, user-generated content via the gh CLI (GitHub repos, issues, discussions) and via web searches (gemini queries), which the agent is expected to read and analyze, exposing it to untrusted third-party content.
Audit Metadata