ClawHub
Back to skill

Security audit

video-transcriber

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate video transcription skill, but it is too broadly scoped and does not clearly disclose how user media and the API key are handled.

Install only if you intend to use it for explicit transcription tasks. Avoid using it with confidential meetings, regulated recordings, client content, or private media unless you know which provider receives the audio or video and are comfortable with its retention and privacy terms.

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

Medium
Confidence
89% confidence
Finding
The 'When to Use' section is overly broad and includes vague triggers like 'User needs ai related functionality' and 'Video operations', which can cause the agent to invoke this skill in situations unrelated to transcription. That increases the chance of unnecessary processing of user media and accidental disclosure of sensitive audio/video content to the transcription backend.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill documentation instructs users to configure an external transcription API key but does not warn that video/audio content may be transmitted to a third-party service. Without a clear disclosure, users may provide sensitive recordings, personally identifiable information, or confidential business conversations without informed consent.

VirusTotal

53/53 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.