pipelines
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted third-party CI/CD pipeline definitions (GitHub Actions, GitLab CI, etc.). This creates a potential surface for indirect prompt injection where instructions embedded in the analyzed code could attempt to influence the agent's behavior during the review.
- Ingestion points: Pipeline definition files (
.github/workflows/*.yml,.gitlab-ci.yml,Jenkinsfile, etc.) as specified inSKILL.md. - Boundary markers: The skill does not explicitly define structural delimiters for the untrusted content in the prompt, but it instructs the agent to "Redact first" and focus on static evidence.
- Capability inventory: The skill uses standard command-line auditing tools (
grep,awk,actionlint,checkov,gitleaks) and writes analysis results to a specific directory (analysis/pipelines/). - Sanitization: The agent is explicitly instructed to redact secrets immediately and avoid echoing them in logs or reports, which significantly reduces the risk of data leakage.
Audit Metadata