skill-design
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts as a procedural guide and methodology framework for designing other agent skills; it does not contain any executable malicious logic or harmful instructions.- [SAFE]: Explicit security guidance is provided in Step 8 (Security and Prompt-Injection Hardening), which instructs developers to define trust boundaries, treat external content as untrusted data, and implement mandatory confirmations for destructive actions.- [SAFE]: Reference files include technical documentation and best practices for configuration optimization (e.g., using regex for permission allowlists) and anti-pattern prevention, all of which enhance the security posture of the resulting skills.- [SAFE]: No indicators of data exfiltration, hardcoded credentials, prompt injection, or unauthorized remote code execution were found within the skill files or scripts.
Audit Metadata