azure-ai-textanalytics-py
Warn
Audited by Gen Agent Trust Hub on Feb 14, 2026
Risk Level: MEDIUMPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION] (MEDIUM): Indirect Prompt Injection Surface (Category 8).
- Ingestion point: The
documentsparameter in analysis methods (e.g.,analyze_sentiment,recognize_entities) accepts untrusted text strings. - Boundary markers: No explicit delimiters or instructions are used to prevent the agent from interpreting instructions embedded within the text.
- Capability inventory: The skill performs network operations to
AZURE_LANGUAGE_ENDPOINT. - Sanitization: No input sanitization is implemented prior to SDK processing.
- [EXTERNAL_DOWNLOADS] (LOW): Trusted Dependency.
- The skill installs
azure-ai-textanalyticsand referencesazure-identity. Both are maintained by Microsoft (Azure), which is a trusted organization, downgrading the download risk.
Audit Metadata