azure-ai-language-conversations-py
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill follows security best practices for Azure development, specifically recommending the use of
DefaultAzureCredentialfor identity-based authentication and using context managers (withstatements) to ensure network connections and credentials are closed properly. - [EXTERNAL_DOWNLOADS]: The skill references official Microsoft SDK packages including
azure-ai-language-conversationsandazure-identity. These are standard dependencies for the described functionality and are sourced from official registries. - [INDIRECT_PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection as it is designed to ingest and process external conversation data.
- Ingestion points: The
queryvariable in theBasic Conversation Analysisexample accepts external text for intent analysis inSKILL.md. - Boundary markers: The code uses structured JSON payloads which provides some isolation, though it does not explicitly define delimiters for the user-supplied text.
- Capability inventory: The skill performs network operations via the
ConversationAnalysisClientto analyze text. - Sanitization: The examples do not demonstrate explicit sanitization of the input text before processing, which is standard for SDK implementation examples.
Audit Metadata