cicd-setup
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes repository manifest files and lockfiles to detect the project stack. This ingestion of untrusted repository content represents a potential indirect prompt injection surface.\n
- Ingestion points: Repository files such as package.json, pyproject.toml, and various lockfiles (package-lock.json, poetry.lock, go.sum, Cargo.lock) as defined in the Detection-First Pipeline Generation section.\n
- Boundary markers: Absent; the skill does not instruct the agent to use specific delimiters or ignore embedded instructions when reading these files.\n
- Capability inventory: The skill uses detected information to generate YAML configurations for the user; it does not invoke shell commands, perform network operations, or write files itself within its logic.\n
- Sanitization: Absent; the skill processes raw file contents to inform its generation logic.\n- [EXTERNAL_DOWNLOADS]: The skill recommends using official GitHub Actions from the 'actions' organization (e.g., actions/checkout, actions/setup-node). These are standard, well-known components for building secure CI/CD pipelines and are considered safe sources.
Audit Metadata