prune-tests
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes repository data including test files and git history, which are potentially untrusted inputs.
- Ingestion points: Test files, git history, and code callers referenced in the repository.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the workflow.
- Capability inventory: File system modification (deleting/consolidating tests), read access to the entire codebase, and command execution (running test suites).
- Sanitization: The skill does not define specific validation or sanitization for the code it processes.
- [COMMAND_EXECUTION]: The workflow instructs the agent to run in-scope tests and record their results, which involves executing code within the local environment.
Audit Metadata