lint
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONNO_CODE
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to dynamically identify and run linting, formatting, and testing tools. This involves executing shell commands with potentially variable arguments derived from the environment.
- [PROMPT_INJECTION]: The skill includes an instruction ('IMPORTANT: If this command is being run as a standalone request, automatically exit') that attempts to override the agent's default control flow and exit behavior.
- [INDIRECT_PROMPT_INJECTION]: The skill processes codebase content that could contain malicious instructions.
- Ingestion points: Phase 2 involves reading codebase files (staged files, PR changes, or the entire repository).
- Boundary markers: There are no specified delimiters or instructions to prevent the agent from obeying commands embedded within the code or comments it processes.
- Capability inventory: The agent can execute commands (linting/testing), write to files (formatting), and perform git operations (commit/stage).
- Sanitization: The instructions do not define any sanitization or validation of file contents before they are processed by tools or the agent.
Audit Metadata