ClawHub
Back to skill

Security audit

glossary-page-generator

Security checks for vulnerabilities and agentic risk

Overview

This is a small glossary SEO guidance skill with no code execution, network access, persistence, or hidden behavior.

Install this for SEO glossary page work. Be aware it may activate on generic wording like definitions or vocabulary, so users should redirect the agent if they are asking about ordinary definitions rather than website glossary content. If project-context files contain sensitive notes, remember the skill may ask the agent to read them for terminology context.

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
90% confidence
Finding

The invocation description says to use the skill when the user wants to create, optimize, or audit glossary page content and structure, and also when they mention broad terms like "definitions," "terminology," or "vocabulary." These terms can appear in many ordinary writing or SEO conversations, making activation boundaries unclear and increasing the risk of unintended invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.