Grasshopper Generator

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:37 PM UTC
• Version:
  1.0.0

Overview

This appears to be a Grasshopper .ghx generation helper whose file-writing behavior is expected for its purpose, with no evidence of hidden exfiltration, persistence, or destructive activity.

Install only if you intend to generate or inspect Grasshopper .ghx files. Save outputs to a deliberate project or temporary folder, avoid overwriting existing work, and review any generated GhPython before running the definition in Rhino/Grasshopper.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 84% confidence
• Finding: The skill explicitly demonstrates saving an output .ghx file and describes file-writing behavior, but no declared permissions or safety constraints are visible in the skill document. Undeclared write capability is risky because an invoking agent or user may not be aware that the skill can create or overwrite local files, which can lead to unintended filesystem changes.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 71% confidence
• Finding: A mismatch between the stated purpose and actual capabilities reduces transparency and can hide additional behaviors from users or orchestrators. In this case, validating existing .ghx files and listing component GUIDs are not inherently dangerous, but undisclosed extra behavior broadens the skill's effective attack surface and may enable unanticipated file access or information disclosure workflows.

Vague Triggers

Medium

• Confidence: 78% confidence
• Finding: Broad trigger phrases increase the chance that the skill is invoked in contexts where the user did not clearly request file generation or code-backed geometry construction. Because this skill can write files and generate executable-adjacent content such as GhPython snippets inside GH definitions, accidental activation is more risky than for a purely informational skill.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The skill instructs saving and delivering .ghx files without warning about file creation, destination, or overwrite behavior. This is dangerous because users may unknowingly cause local file writes or replacement of existing project files, and the generated .ghx may also embed GhPython content that is later executed inside Grasshopper/Rhino workflows.

VirusTotal

65/65 vendors flagged this skill as clean.