agent-manager-skill
Warn
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions require the user to clone a repository from an external GitHub account (
fractalmind-ai) that is not recognized as a trusted organization or well-known service. - [REMOTE_CODE_EXECUTION]: Following the download, the skill provides multiple commands to execute Python scripts (
agent-manager/scripts/main.py) directly from the cloned repository. This pattern involves running arbitrary third-party code that has not been verified for safety.
Audit Metadata