manifest
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
claudeCLI to manage system state, including stopping/installing the gateway service and setting configuration values.- [EXTERNAL_DOWNLOADS]: It installs the 'manifest' plugin via theclaudeCLI. This is the primary functional requirement for connecting the agent to the Manifest platform.- [SAFE]: The skill follows security best practices by prompting the user for credentials rather than hardcoding them, verifying the API key format, and reading local logs solely for verification purposes.
Audit Metadata