azure-speech-to-text-rest-py
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- Credential Management: The skill correctly instructs users to manage sensitive information (Azure Speech keys) using environment variables (
os.environ) rather than hardcoding them in scripts. This is a standard security best practice to prevent accidental credential leakage. - Network Communication: The provided code snippets perform network operations exclusively to official Microsoft service endpoints (
*.stt.speech.microsoft.comand*.api.cognitive.microsoft.com). These are well-known, trusted domains required for the skill's primary functionality. - External Dependencies: The skill utilizes well-established Python libraries (
requestsandaiohttp) for HTTP communication. These are standard packages commonly used for REST API interactions. - Indirect Prompt Injection Surface: The skill processes external audio files provided by the user. While processing untrusted data technically presents an attack surface, the risk is negligible as the skill only performs speech-to-text transcription and returns structured results without executing dynamic commands based on the transcription output.
- Resource Management: The templates follow best practices by using context managers (
withstatements) for file and network operations, ensuring that system resources are properly released.
Audit Metadata