architecture
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is entirely documentation-based, providing architectural patterns, decision trees, and templates for documentation.
- [NO_CODE]: There are no scripts (e.g., .py, .js, .sh) or configuration files that trigger command execution or environment changes.
- [METADATA_POISONING]: The skill's metadata accurately reflects its content, and the instructions to the agent (such as the selective reading rule) are standard operational guidelines for managing context rather than malicious overrides.
Audit Metadata