azure-ai-inference-py
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS] (LOW): The skill installs 'azure-ai-inference' and 'azure-identity' using pip. These packages are published by the Microsoft Azure organization, which is a verified and trusted source per the analysis guidelines.
- [PROMPT_INJECTION] (MEDIUM): The skill facilitates interaction with LLMs using 'ChatCompletionsClient', creating a surface for Indirect Prompt Injection (Category 8). 1. Ingestion points: 'UserMessage' and 'ToolMessage' content in the 'complete()' and 'complete_streaming()' methods. 2. Boundary markers: Absent in the provided snippets. 3. Capability inventory: Network operations (HTTPS requests to Azure AI Foundry endpoints) and model-driven tool execution. 4. Sanitization: No explicit sanitization or input validation logic is present in the example code.
Audit Metadata