ClawHub
Back to skill

Security audit

g1geo

Security checks across malware telemetry and agentic risk

Overview

This skill appears to support a real GEO marketing workflow, but it tells agents to install or update a global CLI without asking and grants broad account-level publishing and analysis authority.

Before installing, understand that this skill may cause your agent to install a global npm CLI, authenticate to a g1geo account, view account-visible products, generate or export reports, and submit content publishing tasks. Only use it if you are comfortable with those account-level permissions, and prefer manually approving the exact install and publish actions.

SkillSpector

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 (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The activation scope is extremely broad, including many loosely related scenarios and an explicit catch-all for 'other' GEO- or AI-search-related tasks. That increases the chance the agent invokes this skill in contexts the user did not clearly request, which can cascade into authentication, external service access, or content distribution actions without sufficiently narrow intent matching.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill explicitly instructs the agent to automatically run a global package installation or upgrade when the CLI is missing, and even says not to ask the user for confirmation first. This is dangerous because it authorizes system modification and execution of newly fetched code from the network, potentially altering the host environment and expanding the blast radius beyond the user’s original request.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.