archetype-review-base
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts as a template for professional domain reviews and does not exhibit any malicious behaviors. It does not include external code downloads, credential exposure, or persistence mechanisms.
- [PROMPT_INJECTION]: The skill identifies a potential indirect prompt injection attack surface by ingesting external code and documentation for review. However, it implements strong boundary markers through its mandatory report structure and focuses on domain-specific heuristics, which mitigates the risk. The capability to use Bash is restricted to specific tools (git and bd), and the ingestion of untrusted data is inherent to the skill's primary function as a reviewer.
Audit Metadata