ClawHub
Back to skill

Security audit

Image Generation

Security checks across malware telemetry and agentic risk

Overview

This skill gives coherent image-generation and validation guidance, with a small local checker that only reports missing or stale generated image files.

Install only if you want repository image-generation workflow guidance and validation for .image.genai prompt files. Run the checker against the project you intend to review, since it recursively scans that root and reports missing or stale generated image siblings.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
This is a mismatch because the declared purpose describes a content-generation or editing skill for documents, PDFs, web assets, and images, while the actual code only performs a filesystem audit of image prompt files and their generated outputs. It does not create or revise documents or images, and its primary function is artifact existence/freshness checking within a directory tree.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.