w-api-test
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides legitimate instructions for performing API and end-to-end testing within a software project. No malicious patterns such as obfuscation or credential theft were found.
- [COMMAND_EXECUTION]: The skill instructs the agent to run testing commands found in the repository documentation or package scripts. This is standard development behavior.
- [INDIRECT_PROMPT_INJECTION]: The skill reads external data from the project repository to guide its actions. Ingestion points: repository files (*.test.ts, e2e specs, and /w-docs). Boundary markers: none. Capability inventory: execution of local testing commands. Sanitization: none. The risk level is low given the intended use in a local development environment.
Audit Metadata