ClawHub
Back to skill

Security audit

Dlazy Image Generate

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed dLazy image-generation CLI integration; it uses network APIs, stored API keys, and optional file uploads in ways that match its stated purpose.

Install this only if you want image-generation requests handled through dLazy. Prompts and any local files you pass as media inputs may be sent to dLazy, usage may consume dLazy credits, and the CLI can store an API key locally unless you use a per-command environment variable.

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
93% confidence
Finding
The trigger keywords are very broad and overlap with ordinary user requests like '生成图片' or '画图', which can cause the skill to activate in situations where the user did not explicitly intend to invoke this specific external CLI workflow. Because activation leads to use of a third-party tool that may require authentication, network access, file uploads, and model selection, accidental triggering increases the risk of unintended API calls, data transfer, or confusing behavior.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The trigger phrases are generic everyday requests like 'generate image' and 'draw picture', which can cause the skill to activate in situations where a user did not explicitly intend to invoke this specific third-party CLI integration. In this skill's context, unintended activation is more concerning because execution can lead to network calls, authentication flows, uploads of local files, and billable API usage through the dlazy service.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.