ClawHub
Back to skill

Security audit

geojson

Security checks across malware telemetry and agentic risk

Overview

This is a small GeoJSON inspection skill that reads user-supplied GeoJSON input and runs a local Python helper without hidden network, credential, persistence, or destructive behavior.

Install if you need local GeoJSON inspection. As with any file-analysis skill, only point it at files you intend to inspect; it does not appear to transmit data or modify files.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.