ClawHub
Back to skill

Security audit

Dlazy Vidu Audio Clone

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly purpose-aligned, but it persists a dLazy API key locally and the inspected CLI package does not substantiate the skill's claim that the saved key is restricted to only the current OS user.

Review the dLazy CLI before installing, and use this only for audio you are allowed to upload for voice cloning. Prefer per-invocation DLAZY_API_KEY or npx if you do not want persistent credentials, and if you use login/auth set, check the permissions on ~/.dlazy/config.json and rotate or revoke the key from the dLazy dashboard if it may have been exposed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
75% confidence
Finding
The trigger keywords are broad and overlap with normal conversation, increasing the chance the skill is invoked when the user did not explicitly intend it. In this skill's context, accidental invocation can cause uploads of local audio paths to third-party services and trigger authenticated API actions that may consume credits or expose sensitive media.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.