code-review-cicd
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted third-party CI/CD configurations, creating a surface for potential indirect prompt injection.
- Ingestion points: External pipeline configuration files (e.g., GitHub Actions YAML).
- Boundary markers: Absent.
- Capability inventory: Restricted to semgrep and gitleaks tools.
- Sanitization: Not explicitly implemented.
Audit Metadata