design-agent
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional documentation and does not include any executable malicious scripts or code.
- [COMMAND_EXECUTION]: Documentation provides instructions for enabling the allow_code_execution feature and explains the security implications of the unsafe execution mode which runs code on the host.
- [EXTERNAL_DOWNLOADS]: Examples illustrate the use of network-based tools like SerperDevTool and provide guidance on creating custom tools using standard libraries such as requests and aiohttp for legitimate data fetching.
- [DATA_EXFILTRATION]: The skill explains how to implement file-reading capabilities and knowledge sources for processing local documentation, which are standard features for agents requiring access to domain-specific data.
Audit Metadata