check-all
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute project-defined scripts such as lint, test, and build. This creates a surface for arbitrary command execution if the project being analyzed contains untrusted or malicious script definitions in its configuration files (e.g., package.json).
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) as it processes and executes instructions from external project data without isolation.
- Ingestion points: Interactions with the project filesystem to detect lockfiles (pnpm-lock.yaml, yarn.lock) and execute scripts via the package manager.
- Boundary markers: None; the skill directly executes scripts defined in external configuration files.
- Capability inventory: Full shell command execution via the Bash tool.
- Sanitization: No validation or sanitization of the content within the project's scripts is performed.
Audit Metadata