agentonboard

Pass

Audited by Gen Agent Trust Hub on Jul 12, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @agentonboard/cli package via npm. This is documented as the primary tool for the skill's functionality and originates from the vendor's own namespace.
  • [COMMAND_EXECUTION]: The skill uses shell commands like aon doctor, aon token get, and aon save. These are standard CLI operations for the intended purpose of authentication management.
  • [CREDENTIALS_UNSAFE]: While the skill involves managing API keys, it follows safe practices by instructing the agent to use a CLI tool that saves keys to the local filesystem (~/.agentonboard/tokens.json) rather than handling or storing them in the prompt context. It specifically mentions that the agent should capture short-lived session tokens rather than static keys.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 12, 2026, 04:34 PM
Security Audit — agent-trust-hub — agentonboard