create-verification-skill
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to discover and execute local build and execution commands (such as package scripts or Makefiles) found within the repository to launch the target application for verification.- [COMMAND_EXECUTION]: As part of the generation process, the agent is instructed to run the generated skill end-to-end (launch, doctor, drive, and cleanup) to prove it functions correctly before handover.- [EXTERNAL_DOWNLOADS]: The skill may involve installing project dependencies if they are missing and required to build or start the application, which is a standard part of a developer-oriented verification workflow.- [SAFE]: The instructions emphasize isolation (e.g., using disposable data directories via /tmp), mandatory teardown of started processes, and avoid any instructions related to external data exfiltration or hardcoded credentials.
Audit Metadata