unit-testing-test-generate
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The CoverageAnalyzer class in SKILL.md utilizes subprocess.run to execute a test_command. If this command is sourced from untrusted user input without sanitization, it could lead to arbitrary command execution on the host environment.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted source code for analysis and test generation. The absence of boundary markers or sanitization logic creates a surface where instructions hidden in code comments or docstrings could influence agent behavior.
- Ingestion points: Source code files parsed in the Analyze Code section of SKILL.md.
- Boundary markers: None identified in the provided instructions.
- Capability inventory: File system read access and subprocess execution via CoverageAnalyzer.
- Sanitization: No sanitization or filtering is performed on the parsed source code content.
- [DYNAMIC_EXECUTION]: The skill generates source code for unit tests using predefined templates. While consistent with its stated purpose, the generation of executable scripts from potentially untrusted analysis data is a known attack surface.
Audit Metadata