ClawHub
Back to skill

Security audit

Image Ppt Maker

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent presentation-image workflow that creates slide images and a local HTML viewer, with no evidence of hidden data access or unsafe behavior.

Safe to install for users who want a structured slide-image and HTML slideshow workflow. Review the generated prompts and images before sharing them, and non-Chinese users may need to ask the agent to translate or restate confirmation prompts in their preferred language.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
90% confidence
Finding
The workflow hardcodes multiple user-review prompts in Chinese while earlier steps allow the user to specify output language and tone. This can override the user's language preference, degrade usability, and create consent/accessibility issues in multilingual contexts, especially for users who cannot read Chinese well enough to safely approve or reject workflow stages.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.