skills/openclaw/skills/agent-manager/Gen Agent Trust Hub

agent-manager

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFECREDENTIALS_UNSAFECOMMAND_EXECUTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill manages sensitive credentials with weaknesses. The setup_agent.sh script generates predictable passwords for new Matrix accounts using a hardcoded suffix ('20260205openclaw'). Furthermore, config_manager.py stores Matrix accessToken values in plaintext in the ~/.openclaw/openclaw.json configuration file.
  • [COMMAND_EXECUTION]: Sensitive information is passed via command-line arguments to shell and Python scripts, which can lead to exposure in system process lists or shell history. Additionally, matrix_register.sh executes curl commands to communicate with external Matrix homeservers for account registration and authentication.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 09:43 PM