ClawHub
Back to skill

Security audit

Geo Conversion Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a marketing-content guidance skill with no hidden execution, credential use, persistence, or destructive behavior found.

Install this if you want help balancing AI citation readiness with conversion goals for marketing pages or content. Be mindful that its trigger language is broad, so use it deliberately for GEO or AI-discovery content work rather than generic sales, ROI, or business-planning tasks.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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
Category
Not specified by scanner
Confidence
83% confidence
Finding

The description frames the skill as applicable whenever content should both rank well in AI answers and drive business outcomes, which is expansive enough to match a wide range of ordinary content tasks. In an agentic environment, overly broad activation guidance can cause unintended tool selection, leading to mis-scoped outputs, unnecessary content rewriting, or interference with more specialized skills.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill says to 'always consider' itself whenever users mention broad business terms like conversion, leads, sales, bookings, or ROI. That creates scope creep: the skill may activate for many generic marketing or business-writing tasks that are not actually GEO-specific, increasing the chance the agent applies unnecessary optimization guidance and overrides more appropriate domain-specific skills or user intent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.