review-architecture
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is used for legitimate code review purposes and utilizes authorized tools (
git,gh,Read,Grep,Glob) to analyze the codebase. - [SAFE]: Network activity is restricted to the GitHub CLI interacting with official GitHub services, which are recognized as well-known and trusted providers.
- [SAFE]: The skill instructions rely on local documentation (
wiki/architecture/*.md) for grounding, ensuring that its analysis is based on project-specific rules rather than untrusted sources. - [SAFE]: Although the skill processes external data in the form of pull request diffs (an indirect prompt injection surface), the available capabilities are restricted to repository analysis, preventing any malicious exploitation. Ingestion points: PR diffs and source code files; Boundary markers: absent; Capability inventory: file system and repository reading; Sanitization: absent.
Audit Metadata