Visual Automation

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Blender automation skill that runs local rendering scripts and writes generated visual assets as expected for its purpose.

Install this only if you want an agent to create Blender scripts and generated assets in your project. Ask for unique filenames or a specific output folder when preserving existing assets matters.

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)

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The skill explicitly instructs the agent to save generated assets directly into the project workspace, which can cause unintended file creation or overwriting without an explicit user confirmation step. In an automation skill that generates code and output files, this increases the risk of silently modifying repository contents, build inputs, or web assets in ways the user may not expect.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal