ClawHub
Back to skill

Security audit

Google Seo Assistant

Security checks for vulnerabilities and agentic risk

Overview

This is a simple SEO guidance skill with no code execution, credential access, persistence, or hidden data handling.

Install this if you want an assistant to give SEO advice when discussing website traffic, rankings, page content, or web copy. Be aware it may surface SEO guidance proactively in some website-review conversations, but the artifact only provides guidance and does not request privileged access.

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 (1)

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill description explicitly says to trigger proactively even when a user only hints at wanting more traffic or better rankings, and also on broad signals like sharing a URL or webpage content. That can cause the SEO skill to activate in contexts where the user did not actually request SEO assistance, increasing the chance of irrelevant guidance, context hijacking, or unintended handling of user content.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.