Back to skill

Security audit

Soilkworks自动化控制

Security checks across malware telemetry and agentic risk

Overview

This SolidWorks helper is purpose-aligned, but generated scripts can control SolidWorks and write files, so users should review them before running.

Install only if you intend to generate local SolidWorks automation scripts. Before running generated Python, confirm dimensions, filenames, output paths, and overwrite behavior, and install pywin32 only from trusted sources.

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 (1)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger words include broad, natural-language phrases such as '画零件', '出工程图', and '机械建模', which can cause the skill to activate in situations where the user did not explicitly intend to invoke automation. In a skill that generates executable Python code to control SolidWorks and save/export files, unintended activation increases the risk of unsafe or surprising actions being suggested or initiated.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.