ClawHub
Back to skill

Security audit

seo-geo

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only SEO/GEO auditing skill whose website checks and optional SEO-tool integrations fit its stated purpose.

Installers should be comfortable with the skill fetching and analyzing the websites or search queries they ask it to audit, and with optional DataForSEO-style tools receiving those domains or queries if configured. No evidence suggests hidden execution, credential use, persistence, or destructive behavior.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · references/google-ai-optimization-guide.md (reported line 102)May include surrounding context.

md
1. **Merchant Center — AI-generated product images:** must carry IPTC
   `DigitalSourceType: TrainedAlgorithmicMedia` metadata. See
   `skills/seo-images/SKILL.md` for the audit + injection pattern.
2. **AI-generated product titles and descriptions:** must be separately
   specified and labeled as AI-generated in the merchant feed.

Static analysis

No suspicious patterns detected.