skill-builder

Pass

Audited by Gen Agent Trust Hub on May 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely informational, providing templates and instructions for developers to build and structure their own AI agent skills.
  • [SAFE]: No network operations, file exfiltration patterns, or credential harvesting techniques were detected in the instructions or reference files.
  • [SAFE]: The skill uses disable-model-invocation: true, which restricts the agent's ability to recursively invoke other models, further reducing the attack surface.
  • [SAFE]: Examples provided within the documentation for package installation or script execution are for illustrative purposes and are not executed by the skill itself.
Audit Metadata
Risk Level
SAFE
Analyzed
May 3, 2026, 07:51 AM