swe-planner
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs legitimate software planning and task management functions without any identified malicious instructions or hidden code.
- [SAFE]: Mandatory human validation (Step 7) is implemented to ensure that all generated outputs are reviewed and approved by the user before any persistence actions are taken.
- [SAFE]: Repository and issue management activities are performed through specialized internal skills, maintaining a restricted and predictable operational scope.
- [SAFE]: Analysis of the workflow confirms that no sensitive system data is accessed, and no unauthorized external network connections are established.
- [SAFE]: The skill's structure and instructions do not contain any obfuscation techniques, credential exposure, or prompt injection vulnerabilities.
Audit Metadata