test
Pass
Audited by Gen Agent Trust Hub on Apr 6, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes standard language-specific test runners and coverage tools such as
go test,pytest,jest,vitest, andcargo testto perform its primary function.\n- [DYNAMIC_EXECUTION]: The skill generates test source files based on project code and executes them locally to verify behavior and coverage measurements.\n- [INDIRECT_PROMPT_INJECTION]: \n - Ingestion points: Reads project source code, configuration files (e.g.,
go.mod,package.json), and test runner output from the local environment.\n - Boundary markers: No explicit boundary markers or instructions to ignore embedded instructions are used when processing source code for test generation.\n
- Capability inventory: The skill has the capability to write files to the local filesystem (in
.agents/test/) and execute shell commands via test runners.\n - Sanitization: The skill does not explicitly sanitize the content of the source code being analyzed for test generation, making it potentially susceptible to malicious instructions embedded in code comments.
Audit Metadata