ClawHub
Back to skill

Security audit

Ai Seo

Security checks for vulnerabilities and agentic risk

Overview

This skill is a content-guidance skill for AI search visibility, with no bundled code, persistence, hidden execution, or credential handling found.

Review the marketing claims and crawler recommendations before applying them, especially robots.txt changes that may allow AI crawlers broader access to public content. From a security perspective, the skill is guidance-only and does not install code or take actions automatically.

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
95% confidence
Finding
The skill description uses very broad trigger phrases such as general requests to 'optimize content' or 'show up in AI answers,' which can cause the agent to invoke this skill for loosely related marketing, SEO, copywriting, analytics, or content-strategy tasks. Over-broad activation is dangerous because it increases the chance the wrong skill handles user input, leading to inappropriate file reads, irrelevant recommendations, or bypass of more specialized skills with narrower guardrails.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The eval explicitly rewards triggering on vague, casual phrasing for AI Overviews visibility without defining tighter boundaries for when this skill should activate versus a broader SEO skill. That can cause overbroad routing, where general SEO or marketing requests are incorrectly handled by the AI-SEO workflow, increasing the chance of misleading advice, missed audits, or policy bypass in systems that depend on precise skill selection.

Static analysis

No suspicious patterns detected.