ClawHub
Back to skill

Security audit

llm-provider Whisper

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be an inconsistent Whisper transcription helper that asks for broad execution, file-writing, API, and credential handling without clear scoping.

Review carefully before installing. Use it only if you are comfortable granting command execution and file write access, and do not provide API keys unless the publisher clarifies why a supposedly local no-key Whisper skill needs them.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The skill makes contradictory claims about whether an API key is required, stating both 'no API key' and later requiring API key configuration. This can mislead users about network use, cost, authentication needs, and data flow, increasing the chance they enable credentials or transmit data under false assumptions.

Intent-Code Divergence

Medium
Confidence
92% confidence
Finding
The FAQ says no extra software is needed even though the skill is described as using the Whisper CLI, which is an external executable dependency. This can cause users to run the skill in an unprepared environment or install missing binaries from untrusted sources when execution fails.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill advertises file writing, API integration, and command execution but does not clearly warn users that these actions can modify local state, invoke external services, or expose user data. In an agent context with read/exec/write tools, this lack of explicit consent boundaries increases the risk of unsafe execution and unintended data disclosure.

Static analysis

No suspicious patterns detected.