cmux-socket-policy
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of markdown documentation and configuration files. It does not contain any executable scripts, binary files, or commands that interact with the network or file system.
- [SAFE]: The instructions specifically promote security best practices, such as the 'Remote Relay Authorization' policy which implements a default-deny stance for remote commands and mandates security reviews for any exceptions to prevent unauthorized execution (addressing GHSA-9vmv-3hjw-j28c).
- [SAFE]: The skill defines operational constraints for the AI agent, such as avoiding main-thread blocking for telemetry and preventing the agent from 'stealing' user focus in the macOS environment, which are benign performance and UX considerations.
Audit Metadata