Azure Ai Transcription Py
PassAudited by VirusTotal on May 12, 2026.
Overview
Type: OpenClaw Skill Name: azure-ai-transcription-py Version: 0.1.0 The skill bundle appears benign. It provides instructions and code examples for using the Azure AI Transcription SDK for Python. The `SKILL.md` file details standard `pip install` commands, environment variable setup (`TRANSCRIPTION_ENDPOINT`, `TRANSCRIPTION_KEY`), and Python code snippets for authentication and transcription. There is no evidence of data exfiltration beyond expected credential usage for the Azure service, malicious execution, persistence mechanisms, prompt injection attempts against the agent, or obfuscation. All content aligns with the stated purpose of an Azure AI Transcription skill.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Installing the wrong or compromised package could affect the user's Python environment.
The skill instructs the user to install an external Python package. This is central to the SDK purpose, but package provenance should be verified because the registry source and homepage are not provided.
pip install azure-ai-transcription
Before installing, verify the package name and publisher from a trusted package index or Azure documentation.
The Azure key may authorize use of the user's Azure AI resource and could incur charges if misused.
The skill uses an Azure subscription key for authentication. This is expected for Azure transcription, but the registry metadata does not declare a primary credential or required environment variables.
TRANSCRIPTION_KEY=<your-key>
Use a least-privileged Azure key if available, keep it out of chat logs and shared files, and rotate it if exposed.
Audio content and related metadata may be processed by Azure's transcription service.
The batch transcription example sends an audio URL to Azure for processing. This is purpose-aligned, but audio may contain sensitive speech or personal data.
content_urls=["https://<storage>/audio.wav"]
Only transcribe audio you are allowed to upload or process, and review Azure data handling settings for your resource.