ClawHub
Back to skill

Security audit

transcribe

Security checks across malware telemetry and agentic risk

Overview

This is a narrow cloud transcription skill that sends chosen audio to SkillBoss for speech-to-text, with no hidden persistence or unrelated access found.

Install only if you are comfortable sending selected audio files to SkillBoss for processing. Avoid confidential, regulated, or consent-sensitive recordings unless SkillBoss data handling terms are acceptable, and keep SKILLBOSS_API_KEY scoped and protected.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly instructs users to base64-encode and upload audio content to a third-party remote API, but it does not warn about privacy, consent, retention, or data handling implications. Audio often contains sensitive personal or confidential information, so omitting a clear transmission/privacy notice can lead to unintentional disclosure.

Natural-Language Policy Violations

Low
Confidence
80% confidence
Finding
The skill advertises translation of audio to English without discussing user opt-in, destination language choice, or the implications of transforming speech content. While not inherently dangerous, this can cause unintended processing or disclosure of content in a different language context without clear user expectation.

VirusTotal

No VirusTotal findings

View on VirusTotal

Static analysis

No suspicious patterns detected.