write-tests
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The skill executes code locally to verify that tests fail as expected (e.g., using
pytest). While this is a form of arbitrary code execution, it is the primary intended purpose of the skill. The risk is mitigated by the context of a development environment. - [INDIRECT_PROMPT_INJECTION] (LOW): The skill reads existing code and user-provided requirements to generate tests. This creates a surface where malicious instructions in project files or requirements could cause the agent to generate and execute harmful code.
- Ingestion points: Reads existing test files in
tests/and requirement descriptions from todos. - Boundary markers: Absent; there are no specific delimiters to separate untrusted data from instructions.
- Capability inventory: File-write access (creating/modifying test files), Command execution (running test suites).
- Sanitization: Absent; the skill does not explicitly validate or sanitize the content of the requirements before processing.
Audit Metadata