gitlab-ci
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains well-structured templates and instructions for generating GitLab CI configurations based on project stack detection.- [DATA_EXPOSURE]: No hardcoded credentials or sensitive file accesses were found. Authentication patterns in the generated YAML use standard GitLab predefined variables.- [COMMAND_EXECUTION]: Shell commands within the reference templates are intended for execution by GitLab Runners during the CI process and are not executed in the agent's immediate environment.- [INDIRECT_PROMPT_INJECTION]: The skill's surface for processing untrusted data (project metadata files) is low risk as it is used for project type classification within a fixed template system.\n- Ingestion points: Reads local project files such as package.json, go.mod, and Cargo.toml to detect the technology stack.\n- Boundary markers: Not used, but stack detection logic is constrained to specific filenames.\n- Capability inventory: Read access to project files; Write access to create .gitlab-ci.yml.\n- Sanitization: Data from local files is used to select appropriate templates rather than being directly executed by the agent.
Audit Metadata