Agent Development

Pass

Audited by Gen Agent Trust Hub on Jul 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional markdown and metadata. It provides templates and best practices for creating agent configurations for Claude Code plugins.
  • [SAFE]: No executable code, remote downloads, or sensitive data access patterns were detected. The scripts mentioned in the documentation (validate-agent.sh, test-agent-trigger.sh) are described as local development tools and are not provided in the analyzed files.
  • [SAFE]: All external references (GitHub URLs and author information) point to the official repository of a trusted organization (Anthropics).
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 12, 2026, 11:25 PM
Security Audit — agent-trust-hub — Agent Development