ClawHub
Back to skill

Security audit

entity-seo

Security checks for vulnerabilities and agentic risk

Overview

This is a single Markdown SEO guidance skill with no code execution, data access, persistence, or privileged behavior.

Safe to install as an SEO reference skill. Users should understand it may be invoked for broad entity or Knowledge Graph wording, but it does not perform actions or access private data.

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
Confidence
95% confidence
Finding
The manifest says to use the skill when the user wants to optimize for "entity recognition" or mentions broad terms like "Knowledge Graph," which can arise in many general SEO, NLP, or search-discussion contexts. The description does not clearly distinguish when this skill should activate versus related skills beyond a single note about structured data, so the trigger scope is ambiguous.

Static analysis

No suspicious patterns detected.