ClawHub
Back to skill

Security audit

Dlazy Kling Image O1

Security checks across malware telemetry and agentic risk

Overview

The skill is a coherent dLazy image-generation wrapper, but it stores an API key locally and the installed CLI code I inspected does not appear to enforce the restricted file permissions claimed by the skill.

Install only if you intend image prompts and referenced local files to be sent to dLazy. Prefer per-invocation DLAZY_API_KEY for sensitive environments, or check and restrict permissions on ~/.dlazy/config.json after login/auth set. Use dry-run when available to review payload and cost before calling the API.

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
92% confidence
Finding
The trigger keywords include broad everyday phrases such as '生成图片、编辑图片' and '文生图、图生图', which can cause the skill to activate in contexts where the user did not specifically intend to use this third-party CLI/API. In this skill, accidental invocation is more concerning because execution may upload local files and send prompts to external services, creating privacy, cost, and unintended action risks.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger keywords are broad enough to match common user requests like 'generate image' or 'edit image', which can cause this skill to be invoked when a user did not specifically intend to use the dLazy tool. Because the skill performs networked operations, may upload local files, and encourages authentication/setup, accidental invocation can expose prompts, file paths, or media to a third-party SaaS unexpectedly.

VirusTotal

52/52 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.