ClawHub
Back to skill

Security audit

all-in-one-domain-website-tools

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple URL router for domain, naming, and logo tools, with limited privacy considerations around putting user text into generated links.

Install only if you are comfortable using Nameslink-hosted tools for domain, naming, and logo workflows. Review generated links before opening them, especially when the link includes business ideas, project descriptions, or other sensitive text.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger list includes generic terms such as 'contains', 'logo', and broad naming/search phrases that can match many unrelated user requests, causing the skill to activate outside its intended scope. Unintended activation can misroute conversations and may cause the agent to extract user-provided context into outbound URLs unnecessarily, increasing privacy and prompt-routing risk.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The instruction explicitly allows inferring missing parameters from user context and summarizing project descriptions into URL parameters, but it does not warn users that their freeform input may be transformed and embedded into a third-party URL. This can expose sensitive or proprietary business details in query strings or paths, which may be logged by browsers, intermediaries, and the destination service.

Static analysis

No suspicious patterns detected.