generate-tests
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source code and configuration files which could contain instructions to manipulate the agent's behavior. Ingestion points: Reads target code and project configuration files (e.g., package.json, pyproject.toml) in Steps 1 and 2. Boundary markers: Absent. Capability inventory: File system read/write access and shell command execution for running tests. Sanitization: None documented.
- [DYNAMIC_EXECUTION]: The skill involves generating new test scripts at runtime based on the analyzed project context.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to run the project's test suite in Step 5.
Audit Metadata