setup
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONCREDENTIALS_UNSAFEEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to execute local Python and Node.js scripts (look_tongji.py and vision.mjs) located within the project repository to perform environment checks and verification tasks.
- [CREDENTIALS_UNSAFE]: The skill facilitates the configuration of API keys for various vision providers but correctly instructs the agent to use secure methods, such as environment variables or interactive terminal prompts, rather than requesting them through the chat interface.
- [EXTERNAL_DOWNLOADS]: The setup process verifies the installation of well-known and trusted Python libraries including requests, playwright, and markitdown.
Audit Metadata