ClawHub
Back to skill

Security audit

Ai Seo

Security checks for vulnerabilities and agentic risk

Overview

This is a non-executable AI SEO guidance skill with disclosed, purpose-aligned behavior and no evidence of hidden access, persistence, or unsafe execution.

Installers should understand that this skill may activate for a wide range of AI visibility and AI citation questions, and that it may read existing product marketing context files to tailor its advice. Review its crawler recommendations carefully because allowing AI bots can affect both citation visibility and content reuse exposure.

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
Confidence
93% confidence
Finding
The skill description contains very broad trigger phrases and repeated 'use this whenever' language that can cause the skill to activate for loosely related requests, including generic SEO, content, or AI-assistant questions. Over-broad activation is dangerous because it can route users into the wrong skill, causing inappropriate guidance, reduced reliability, and possible bypass of more specialized skills that would apply stricter or safer workflows.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The evaluation explicitly rewards triggering on 'casual phrasing' for AI Overviews visibility requests, which broadens activation criteria without strong boundaries around when this skill should apply versus adjacent skills like general SEO. In a routing or agent-selection context, overly permissive triggers can cause misclassification of user intent, leading the agent to apply the wrong workflow, produce lower-quality guidance, and potentially ignore more appropriate safeguards or domain-specific checks from another skill.

Static analysis

No suspicious patterns detected.