ClawHub
Back to skill

Security audit

fun-denoise

Security checks across malware telemetry and agentic risk

Overview

This is a coherent cloud audio-denoising skill, but users should know selected recordings are processed through Alibaba DashScope.

Install only if you are comfortable sending chosen audio files to Alibaba DashScope for processing. Avoid sensitive, regulated, or confidential recordings unless you have approval and have reviewed the provider's privacy and retention terms; use a protected API key and trusted Python environment.

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
95% confidence
Finding
The skill clearly instructs users to install cloud SDK dependencies, set a DashScope API key, and use a WebSocket-based remote denoising service, but it does not explicitly warn that uploaded audio content is sent off-device to a third-party cloud service for processing. This can mislead users into sharing sensitive recordings such as meetings, interviews, or personal voice data without informed consent, creating privacy, confidentiality, and compliance risks.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The tool streams user audio to an external service via the Denoise client/WebSocket flow, but the CLI does not clearly disclose that potentially sensitive recordings leave the local machine. This can expose private conversations, meetings, or personal data to third-party processing without informed user consent, which is especially risky given the skill's recording and speech-related use cases.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal