azure-ai-contentsafety-py
Pass
Audited by Gen Agent Trust Hub on Feb 14, 2026
Risk Level: LOWEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- EXTERNAL_DOWNLOADS (INFO): The skill installs the 'azure-ai-contentsafety' package. As Microsoft is a trusted organization, the risk is negligible.
- PROMPT_INJECTION (LOW): The skill contains an indirect prompt injection surface (Category 8) as it processes untrusted external content.
- Ingestion points: The analyze_text and analyze_image functions accept arbitrary external data.
- Boundary markers: No specific delimiters or safety instructions are used to wrap processed content in the provided code snippets.
- Capability inventory: The skill returns classification results (severity levels and categories) to the agent, which can influence downstream reasoning.
- Sanitization: No sanitization is applied to the input content before processing.
Audit Metadata