agent-designer
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a development utility for system designers and does not contain any executable malicious patterns or hidden instructions.
- [SAFE]: No unauthorized data access, sensitive file exposure, or hardcoded credentials were identified in the source code or provided assets.
- [SAFE]: Python scripts (agent_planner.py, tool_schema_generator.py, agent_evaluator.py) use standard library modules for local data processing and do not perform any remote code execution or external network requests.
- [SAFE]: The skill documentation explicitly promotes security best practices, including input validation, content filtering, and the use of guardrails for agent-based systems.
- [SAFE]: Data ingestion is limited to local JSON parsing for design purposes, with no risk of indirect prompt injection affecting the local execution environment.
Audit Metadata