ClawHub
Back to skill

Security audit

seo-page

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward SEO page-audit skill with no bundled code, persistence, or hidden behavior, though its activation wording is broader than ideal.

Installers should be aware that a plain single-URL request might activate this skill and produce an SEO audit. Use it when you intend SEO analysis, and avoid sending private or authenticated pages unless you are comfortable sharing rendered HTML for review.

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

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill’s invocation guidance includes very generic phrases like "analyze this page," "check this page," and accepting any single URL, which can overlap with common user requests and cause the skill to activate when the user did not explicitly intend an SEO audit. In an agent setting, overbroad triggers can route unrelated browsing or analysis tasks into this skill, increasing the chance of unintended network access, incorrect task selection, or exposure of user-supplied URLs to external integrations.

Content

No source excerpt is available for this finding.