hosted-agents
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides high-level architectural guidance and best practices for designing hosted agent environments, such as image pre-building, warm-up strategies, and session isolation.
- [EXTERNAL_DOWNLOADS]: The skill references external resources from well-known and reputable services including Cloudflare, Modal, and SST (OpenCode). These links are informational and provided for technical context.
- [COMMAND_EXECUTION]: While the skill discusses the implementation of sandboxes and the execution of build commands within those sandboxes, it does not include any malicious or unauthorized command execution instructions.
Audit Metadata