ClawHub

Manim Animation Cn

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Manim video helper that renders local animation outputs and optionally uses TTS, with no evidence of hidden, destructive, or unrelated behavior.

Install this only if you are comfortable adding Manim, FFmpeg, codec/font dependencies, and running generated Python scene files locally. Use offline pyttsx3 for private narration, avoid sending secrets or confidential text to cloud TTS providers, and clear media/voiceover caches if narration content is sensitive.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill clearly instructs the agent to read and write files and execute shell commands (`python3`, `manim`, `ffmpeg`, package installs), but it does not declare corresponding permissions. This creates a capability transparency problem: a user or platform may invoke the skill without understanding that it can modify the filesystem and run local commands, increasing the chance of unsafe or unexpected execution.

Vague Triggers

Medium
Confidence
80% confidence
Finding
The trigger description is broad enough to match generic requests like 'create animation video' or educational video generation, which could cause this skill to activate outside its intended narrow Manim use case. Over-broad routing increases the chance that a shell-capable, file-writing skill is selected for ordinary requests, expanding exposure unnecessarily.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The guide recommends network-based TTS providers such as gTTS, Azure, OpenAI, and ElevenLabs without clearly warning that narration text may be transmitted to third-party services. If users include sensitive, proprietary, or personal content in scripts, this can cause unintended data disclosure outside the local environment.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal