ask
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns such as prompt injection, obfuscation, or persistence mechanisms were detected. The skill implements a standard persona-based architectural review workflow.
- [SAFE]: The skill operates exclusively on local documentation and source code files for context, with no evidence of credential exposure, external network operations, or data exfiltration.
- [SAFE]: Potential indirect prompt injection risks from user queries are mitigated by the use of XML-style boundary tags and explicit instructions for the agent to maintain skepticism and verify every claim against codebase evidence.
Audit Metadata