ClawHub
Back to skill

Security audit

geo-schema

Security checks across malware telemetry and agentic risk

Overview

This skill performs a structured-data audit and writes a local report, with no evidence of hidden, destructive, or unrelated behavior.

Before installing, expect the skill to fetch target web pages, run schema-related commands, and save a local GEO-SCHEMA-REPORT.md. Ask the agent to confirm before overwriting an existing report if that matters in your workflow.

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

Low
Confidence
93% confidence
Finding
The skill instructs the agent to generate and write `GEO-SCHEMA-REPORT.md` into the workspace without any explicit requirement to obtain user confirmation first. Even though the intended file is a report, silent workspace modification can surprise users, overwrite existing files, or be chained with broader write-capable behavior in automated runs.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.