build-cognitive-decision-record
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely focused on documentation standards and architectural best practices. It does not contain executable code, network operations, or sensitive data access patterns.
- [SAFE]: The provided templates and examples focus on software engineering methodology (e.g., ORM selection, decision rationale) and do not introduce any prompt injection or obfuscation vectors.
- [SAFE]: The skill operates within a controlled documentation environment, defining output paths for markdown files (
docs/features/<name>/adr/) which is a standard practice for ADRs.
Audit Metadata