ClawHub
Back to skill

Security audit

Geo Local Optimizer

Security checks across malware telemetry and agentic risk

Overview

This skill is a local search optimization planning guide and does not show hidden data access, credential use, persistence, or autonomous account-changing behavior.

Install this if you want structured local SEO/GEO planning. Be prepared to share business-location details such as addresses, service areas, hours, listings, and review strategy with the agent, and verify any marketing, schema, or listing recommendations before publishing them publicly.

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
92% confidence
Finding
The skill’s trigger criteria are intentionally expansive, instructing invocation whenever a request merely suggests local business discovery, maps, reviews, or geography-linked marketing goals. In an agent setting, this can cause over-selection of the skill on loosely related prompts, leading to inappropriate workflow execution, unnecessary data collection, and reduced routing precision rather than direct code-execution risk.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The 'When to use this skill' section reinforces broad, ambiguous invocation rules such as strongly considering the skill whenever a user mentions geographic context plus discoverability, even without explicit local SEO language. This increases the chance of prompt-routing overreach, where the agent applies a complex local-optimization workflow to marginally relevant conversations and exposes users to mis-scoped advice or unnecessary information requests.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal