ClawHub
Back to skill

Security audit

AI Citations Check: Does ChatGPT Cite You - SEOmatic

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed SEO analytics integration that reads scoped SEOmatic citation and traffic data, with no bundled code or hidden persistence.

Before installing, confirm you trust SEOmatic with access to your connected site's citation, traffic, and analytics data, and prefer OAuth over a long-lived API key where available. The reviewed artifact is read-focused and purpose-aligned, but it still exposes business analytics through the connected service account.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 36)May include surrounding context.

md
Every read here is FREE and reads stored first-party data. Nothing triggers a
scan or spends credits. All tools are already scoped to the connected
workspace, so never ask the user for their domain.

There are two different kinds of evidence, and confusing them is the main way
this answer goes wrong:

Static analysis

No suspicious patterns detected.