ClawHub
Back to skill

Security audit

SEO Content Brief and Draft Scoring - SEOmatic

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed SEO content-brief skill that uses SEOmatic and Search Console data for content planning, with no bundled code or hidden local behavior.

Install this only if you intend to connect SEOmatic to a site and use its Search Console and SEO data for content planning. For generic writing or editing requests, confirm whether you want SEOmatic involved before letting it query site data or spend credits on SERP, keyword, or article-generation actions.

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
93% confidence
Finding

The skill description uses broad trigger phrases such as requests for a content brief, article outline, what to include in a post, or checking a draft before publication. This can cause the skill to activate for common writing tasks beyond narrowly SEO-focused use cases, leading to unnecessary access to connected SEO/GSC data and external MCP actions when the user may have intended a generic writing request.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.