code-review-cicd
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides educational content and methodologies for security auditing of CI/CD pipelines. No malicious instructions, obfuscation, or unauthorized access patterns were detected.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted repository configuration data (YAML workflows) as part of its auditing process, creating a potential surface for indirect prompt injection.
- Ingestion points: Reads repository CI configuration files (GitHub Actions, GitLab CI, Jenkins, CircleCI) and PR event data as described in
SKILL.md. - Boundary markers: None provided in the instructions to separate repository content from agent instructions.
- Capability inventory: Employs
semgrepandgitleaks(defined inallowed-tools) to analyze file content. - Sanitization: No specific sanitization or escaping of external configuration content is mentioned.
Audit Metadata