ClawHub

Geo Content Optimizer

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a content-optimization guide for improving AI-search visibility, with no artifact-backed evidence of exfiltration, destructive behavior, hidden execution, or credential abuse.

Install if you want help optimizing publishable content for AI citation and search-answer visibility. Be aware that its broad trigger wording may make it activate for general AI-content requests, so confirm that you actually want GEO-style optimization before following its recommendations.

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
89% confidence
Finding
The skill’s when-to-use guidance is broad enough that it may be invoked for many generic AI-content requests, not just narrow GEO/citation-optimization tasks. Over-broad routing can cause unintended activation, leading the agent to apply specialized persuasive/visibility-optimization behavior in contexts where the user did not clearly request it.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger list contains many ambiguous phrases such as 'optimize for AI' and 'AI optimization' that can match ordinary requests unrelated to this skill’s intended scope. In an agentic system, ambiguous triggers increase the chance of incorrect skill selection, which can distort outputs, override better-matched skills, or steer users toward manipulative visibility tactics without sufficient context.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal