ClawHub
Back to skill

Security audit

Azure Transcription Tool Free

Security checks across malware telemetry and agentic risk

Overview

The skill is not clearly malicious, but it needs review because it is a cloud audio-transcription tool whose trigger text incorrectly points to translation/localization and whose privacy implications are under-emphasized.

Install only if you specifically want Azure-based speech-to-text. Do not rely on this skill for translation or localization tasks. Before using it with meetings, interviews, or other sensitive recordings, confirm you are allowed to upload the audio to Blob storage and process it with Azure, and protect the TRANSCRIPTION_KEY as a credential.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

High
Confidence
75% confidence
Finding
The trigger condition is overly broad and mismatched, instructing use for translation and localization tasks outside the actual capability of the skill. In an agent setting, this can cause unintended execution, routing sensitive content to the wrong tool, or user confusion that results in privacy-impacting cloud submission of data under false assumptions.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill omits a clear warning that audio URLs and transcript content are sent to Azure cloud services for processing. This is dangerous because users may provide sensitive recordings without informed consent, creating privacy, compliance, and data-governance risks in contexts such as meetings, interviews, or internal recordings.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.