The Agent Skills Directory

[Secure Authentication Patterns]: The skill provides documentation on using Azure's Managed Identity and Role-Based Access Control (RBAC), which helps prevent the exposure of sensitive credentials by avoiding hardcoded keys in production environments.\n- [Official Library Dependencies]: The instructions include references to official Azure SDKs available on standard package managers like pip and npm. These are verified vendor resources necessary for interacting with Azure services.\n- [Indirect Prompt Injection Surface]: By facilitating the ingestion of data from search results and transcriptions, the skill establishes a surface where untrusted content could potentially influence agent behavior. Reviewing and sanitizing data retrieved from external sources is a standard precaution.\n
Ingestion points: Data entering via search queries, document analysis, and speech transcriptions.\n
Boundary markers: The provided instructions do not include specific delimiters or instructions to ignore embedded commands.\n
Capability inventory: The skill utilizes tools for searching indexes, managing speech synthesis, and performing transcription.\n
Sanitization: No explicit sanitization or validation steps are provided in the quick-start code snippets.

azure-ai