restaurant-booking

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses Python and curl commands to manage API authentication and perform browser automation tasks. These commands are standard for the skill's stated purpose and use legitimate endpoints associated with the vendor (gooseworks.ai).
  • [CREDENTIALS_UNSAFE]: The skill correctly instructs the agent to retrieve API keys from a local configuration file (~/.gooseworks/credentials.json) rather than hardcoding them in the instructions. This is a secure credential management practice.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 05:43 PM
Security Audit — agent-trust-hub — restaurant-booking