add-new-feature
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses a structured orchestration pattern with clear boundary markers (e.g., <feature_request>, <quality_vigilance>) to separate instructions from untrusted data input.- [SAFE]: File system operations are restricted to a specific local project directory (~/.dh/projects/) for state management, with no evidence of sensitive file access or traversal.- [SAFE]: External interactions are limited to GitHub issue and artifact management via designated MCP tools, which aligns with the skill's stated purpose.- [SAFE]: No obfuscated content, hardcoded credentials, or dangerous command execution patterns (such as curl|bash) were found.
Audit Metadata