writing-claude-directives

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains educational and meta-instructional content for prompt engineering and agent management. No malicious patterns, data exfiltration attempts, or unauthorized command executions were found.
  • [SAFE]: Includes informational references to official Anthropic documentation and well-known public GitHub repositories for best practices.
  • [SAFE]: The skill demonstrates a security-conscious approach by explicitly requiring the use of a prompt security hardening skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 12:50 PM