comprehensive-test
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to initiate development environments and run testing scripts as part of the CLI and Web App testing paths.
- [PROMPT_INJECTION]: The skill processes instructions from the local ".turbo/test-plan.md" file. As this data influences agent actions, it represents an indirect prompt injection surface. However, this is part of the intended testing functionality and limited to the user's workspace. Evidence Chain: 1. Ingestion points: .turbo/test-plan.md; 2. Boundary markers: None; 3. Capability inventory: Shell execution, file system modification, browser/UI control; 4. Sanitization: None.
Audit Metadata