agent-designer
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides documentation and local CLI scripts for agent system design and evaluation. Analysis of the scripts (
agent_planner.py,agent_evaluator.py,tool_schema_generator.py) shows they are standard Python tools using built-in libraries likejson,argparse, andre. - [SAFE]: No network exfiltration or unauthorized file access was detected. The tools operate strictly on input files provided by the user and write to local output paths.
- [SAFE]: No obfuscation, prompt injection, or remote code execution patterns were found in the skill metadata, documentation, or code.
- [SAFE]: Examples in the documentation reference well-known and trusted AI service libraries (OpenAI and Anthropic), following standard integration patterns.
Audit Metadata