The Agent Skills Directory

[SAFE]: The skill is a collection of Markdown documentation and code snippets for integrating with Azure AI services like Search, Speech, OpenAI, and Document Intelligence.
[PROMPT_INJECTION]: No evidence of prompt injection or behavior override instructions found.
[CREDENTIALS_UNSAFE]: No hardcoded credentials or secrets were detected. The skill includes a dedicated 'Authentication Best Practices' guide that explicitly recommends against hardcoding secrets and encourages the use of Managed Identities and Azure RBAC.
[DATA_EXFILTRATION]: No suspicious network operations or attempts to access sensitive local files (e.g., SSH keys, environment files) were found.
[REMOTE_CODE_EXECUTION]: No remote script downloads or dynamic code execution patterns (like eval or exec) were identified. All documented code uses official Azure SDKs.
[COMMAND_EXECUTION]: The skill mentions standard Azure CLI commands (az search, az cognitiveservices) which are expected for managing Azure resources.

azure-ai