azure-ai-agents-python

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). This documentation contains deliberate high-risk patterns — direct eval() usage on external input plus built-in tools that execute arbitrary Python (CodeInterpreterTool/FunctionTool), access and download uploaded files, and call external APIs/services — which collectively enable remote code execution and data exfiltration if abused.