ClawHub
Back to skill

Security audit

Dlazy Viduq2 T2i

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Vidu Q2 image-generation wrapper that sends prompts and selected image inputs to dLazy, with a minor overbroad-trigger caution.

Install only if you are comfortable using dLazy's hosted service for image generation. Prompts and any local files you pass as image inputs may be uploaded to dLazy, and the CLI can store an API key locally unless you choose the environment-variable option. Prefer invoking it explicitly with Vidu Q2 or dlazy terms to avoid accidental use on generic image requests.

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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger keywords are broad and overlap with common user intents like generating or editing images, which can cause the agent to invoke this skill in situations the user did not explicitly intend. Because this skill can upload local files and send prompts to a third-party SaaS, overly permissive activation increases the chance of unintended data exposure or unnecessary external API calls.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The trigger keywords are broad enough to match generic requests like 'generate image' or 'edit image', which can cause the skill to activate in situations the user did not explicitly intend. Because this skill sends prompts and local file paths to a third-party hosted API, accidental activation can result in unintended data disclosure, external network calls, or unnecessary paid usage.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.