ClawHub
Back to skill

Security audit

seo-audit

Security checks for vulnerabilities and agentic risk

Overview

The skill is a transparent SEO audit workflow that crawls websites and creates local reports, with no evidence of hidden or malicious behavior.

Install this if you want a full SEO audit skill. Before running it, confirm the target site, be aware it can crawl many pages and create local screenshots and reports, and only enable Google, DataForSEO, Moz, or Bing credentials for sites where that access is appropriate.

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
95% confidence
Finding

The description includes very broad invocation cues like 'audit,' 'analyze my site,' and 'website health check,' which can cause the skill to be selected in situations where the user did not intend a deep crawl-and-write workflow. Because this skill performs expansive actions such as crawling up to 500 pages, delegating many subagents, and generating files, accidental invocation can lead to unnecessary network activity, cost, and unintended data collection.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly writes multiple artifacts, findings, screenshots, and optional reports to local paths without stating that files will be created or asking for user consent. This is risky because users may not expect persistent local output, and screenshots or audit data can capture sensitive page content or internal site information that remains stored on disk.

Content

No source excerpt is available for this finding.