ai-behavior-engineer

Warn

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands (cat) to access local configuration files such as .production-grade.yaml and .forgewright/project-profile.json. It also provides instructions to execute a local test script using node scripts/test-gemini-behavior.js.
  • [EXTERNAL_DOWNLOADS]: The skill references and imports the forgewright-gemini-sdk Node.js package. This is an external dependency from an unverified source that is not associated with an established trusted organization or well-known service.
  • [SAFE]: The game AI implementation logic in SKILL.md, including Behavior Tree, GOAP, and Utility AI architectures, consists of standard development patterns and contains no malicious code or suspicious system interactions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 22, 2026, 08:30 AM
Security Audit — agent-trust-hub — ai-behavior-engineer