ClawHub
Back to skill

Security audit

tools-page-generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a non-executable guide for planning free tools pages, with only minor routing ambiguity in its trigger description.

Before installing, consider whether you want a broadly triggered free-tools-page strategy helper. It appears safe, but its invocation wording may make it activate for generic toolkit or free-tool requests where a more specific skill would fit better.

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
91% confidence
Finding

The invocation description is broad enough to match common terms like "free tools," "toolkit," or generic page requests, which can cause the agent to activate this skill outside its intended niche. This is dangerous because misrouting can suppress better-matched skills, produce irrelevant guidance, and create unreliable agent behavior at scale, even though the content itself is not overtly malicious.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.