write-tests
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [Intended Command Execution]: The skill instructs the agent to execute commands to run and verify tests (e.g., using
pytest). This is a standard part of the software development lifecycle and is used here to ensure test validity. - [File System Interaction]: The instructions allow the agent to read existing tests and create new test files in the project's directory. This behavior is appropriate for its stated purpose as a test generation tool.
- [Contextual Requirement Handling]: The skill processes project-specific requirements to define test cases. This interaction is central to the skill's functionality and follows typical agent-assisted development workflows.
Audit Metadata