ci-test-matrix
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from project files (such as package.json, pyproject.toml, and docker-compose.yml) via the Read and Grep tools. This creates an indirect prompt injection surface where malicious instructions embedded in a project's metadata or configuration could influence the agent's behavior during analysis.
- [SAFE]: The skill follows the principle of least privilege by restricting its toolset to Read, Grep, and Glob, which prevents data exfiltration or command execution. It also includes explicit safety instructions for the agent to use secrets for credentials and avoid including production environment information in the output.
Audit Metadata