agent-builder

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as an instructional resource and template library for agent development.
  • [SAFE]: System prompt examples incorporate security best practices, including constraints against unauthorized modifications and checklists for secret detection (e.g., OWASP Top 10 focus and secret detection patterns).
  • [SAFE]: Tool configurations consistently recommend the principle of least privilege, suggesting read-only access (Read, Grep, Glob) or granular command scoping for sensitive tools like Bash (e.g., Bash(git diff:*)).
  • [SAFE]: No obfuscated content, hardcoded credentials, or suspicious external dependencies were found. The mention of standard development tools like npm and pytest is consistent with the skill's purpose as a developer productivity tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 08:08 AM