issue
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were identified. The skill incorporates multiple safety-first design principles.
- [PROMPT_INJECTION]: Evaluated the potential for indirect prompt injection via user descriptions and session data. This is considered SAFE due to the presence of a 'plan-first' requirement and explicit human confirmation before execution.
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute standard development utilities such as the GitHub CLI, jq, and git. The behavior is SAFE as all commands are previewed to the user and require approval before being run.
Audit Metadata