ClawHub
Back to skill

Security audit

Whisper v1转录免费版

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a local Whisper transcription helper, but its documentation is broad and inconsistent enough that users should review it before installing.

Install only if you intend to use it for local audio/video transcription or subtitle generation, and treat any API key language as unreliable unless clarified by the publisher. Review commands before running them, especially package installation, sudo, and any command that processes private media files.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The documentation contradicts itself on whether the skill is fully local and requires no API key, while later sections say an API key is required and refer to LLM/API dependencies. This can mislead users into supplying secrets unnecessarily or trusting incorrect network/data-flow assumptions, which is a real security and operational risk for an exec-capable skill.

Intent-Code Divergence

Medium
Confidence
92% confidence
Finding
The skill is advertised as a simple local single-file transcription tool, but later text claims broad automation, batch processing, API aggregation, and other unsupported capabilities. Overstating capabilities can cause the agent or user to invoke the skill in inappropriate contexts, increasing the chance of unsafe command execution, data mishandling, or accidental overreach beyond the tool's actual boundaries.

Vague Triggers

High
Confidence
97% confidence
Finding
The top-level description says to use this skill for broad LLM calling, intelligent dialogue, agent orchestration, and LLM applications, even though the skill's actual function is local Whisper transcription. An overly broad trigger on a skill with exec access can cause unintended invocation in unrelated tasks, leading the agent to run local commands in contexts where no command execution should occur.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger condition says the skill should be used for text translation, multilingual conversion, and localization, which is broader than the documented audio-transcription use case. This ambiguity increases the chance the skill is selected for general translation tasks and may prompt unnecessary exec activity or incorrect handling of non-audio inputs.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.