Security audit

Geo Cn

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed GEO audit and content-planning workflow with local recordkeeping, and I found no hidden execution, credential access, exfiltration, or destructive behavior.

Install only if you are comfortable having brand/client audit records saved locally under ./geo-clients/ or a configured GEO_CLIENTS_DIR. For client work, confirm consent before storing company details, competitors, websites, channels, and monitoring history.

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 (2)

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The trigger phrases are broad enough to activate on ordinary conversation such as general questions about AI visibility or brand mentions, which can cause the skill to run unexpectedly. In this skill, unexpected activation matters because later steps collect business information and may persist records to local storage, increasing the chance of unintentional data handling.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The skill instructs collecting identifiable client business data and later storing it in local JSON files, but it does not require a clear user-facing consent notice before persistence. This creates a real privacy and data-governance risk because users may disclose company, brand, region, website, competitors, and operational history without realizing the information may be retained on disk.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.