ClawHub
Back to skill

Security audit

nielsen-ui-review

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only guide for structured UI usability reviews and does not request risky system access.

Install this if you want the agent to give structured usability feedback on provided UI images or screens. Expect it to ask clarification questions and produce Nielsen-heuristic findings; it should not need credentials, command execution, or access to unrelated local 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
Category
Not specified by scanner
Confidence
91% confidence
Finding

The invocation description says to use the skill when the user asks to 'review, critique, evaluate, audit, or assess' a UI and lists broad examples like 'review this UI' and 'give me UI feedback.' Although the domain is UI-focused, these triggers are still quite general and the file does not provide negative examples or clearer exclusion boundaries for when this skill should not activate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.