hai-architecture
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed for architectural analysis and design guidance. It does not contain any instructions for executing remote code, accessing sensitive system files, or performing network operations to untrusted domains.
- [SAFE]: The instructions include a "Ground Every Claim in Evidence" rule which serves as a defensive mechanism against hallucinations and potential indirect injections by requiring the agent to verify all claims against the actual source code.
- [SAFE]: No obfuscation techniques, prompt injection attempts, or persistence mechanisms were found in the skill's files.
- [SAFE]: The skill defines clear boundaries for its operation and explicitly refers users to other specialized skills for tasks like naming or local code-style reviews, adhering to the principle of least privilege in its intended use.
Audit Metadata