agent-manager-skill

Fail

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to clone a codebase from an unverified external GitHub repository (github.com/fractalmind-ai/agent-manager-skill.git). This source does not originate from a recognized or trusted organization.
  • [REMOTE_CODE_EXECUTION]: Following the download, the skill executes Python scripts (agent-manager/scripts/main.py) from the unverified repository. This allows for the execution of code provided by an external third party within the user's environment.
  • [COMMAND_EXECUTION]: The skill relies on executing local system commands such as tmux and python3. Additionally, it mentions 'cron-friendly scheduling' for recurring tasks, which involves modifying system crontabs. This functionality serves as a persistence mechanism, allowing code to run automatically across sessions.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Aug 5, 2026, 06:48 AM
Security Audit — agent-trust-hub — agent-manager-skill