clean-architecture-review
Pass
Audited by Gen Agent Trust Hub on Aug 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a comprehensive safety framework including policy BF-SECURITY-1 for secret redaction and BF-UNTRUSTED-1 for resisting indirect prompt injection within analyzed artifacts.
- [SAFE]: Architecture analysis is conducted using standard, read-only inspection tools (e.g., ripgrep, dependency analyzers) as outlined in the review workflow, with command execution explicitly limited by policy BF-COMMAND-1.
- [SAFE]: Persistence and inter-skill communication are handled through an optional, local file-based workflow (.ai-workflow/) that follows a lock-safe protocol to ensure data integrity without external network requirements.
Audit Metadata