azure-ai-language-conversations-py
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [Natural Language Processing Surface]: The skill is designed to ingest and analyze user-provided conversation text, which represents an indirect prompt injection surface. * Ingestion points: User query text is passed into the ConversationAnalysisClient in SKILL.md and references/non-hero-scenarios.md. * Boundary markers: The skill uses a structured JSON payload format defined by the SDK, providing clear data separation. * Capability inventory: The skill is limited to performing network requests to Azure AI Language services; it does not perform local command execution, file system modifications, or sensitive data access. * Sanitization: The provided code examples process user input as text without explicit sanitization or filtering.
- [Credential Management]: The skill correctly identifies and promotes the use of DefaultAzureCredential and environment variables. This approach is a security best practice that avoids hardcoding secrets and facilitates the use of managed identities in production environments.
- [Official SDK Usage]: The implementation relies on official Azure SDKs maintained by the vendor, ensuring that the integration with cloud services follows supported and secure communication protocols.
Audit Metadata