ClawHub
Back to skill

Security audit

UX Baseline Check

Security checks for vulnerabilities and agentic risk

Overview

This skill is a UX checklist for frontend work and does not contain code, persistence, credential handling, or hidden data flows.

Install this if you want agents to consistently check frontend states before shipping. Be aware it may make agents apply a fairly strict UX checklist across many visual tasks, so users who want lighter frontend guidance may prefer narrower activation wording.

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
96% confidence
Finding

The skill declares itself as a core pack that is 'always active' for 'ALL visual and frontend work,' which creates an unnecessarily broad and ambiguous activation scope. Over-broad auto-activation increases the chance the agent will apply this checklist in irrelevant contexts, causing instruction bleed, priority conflicts with other skills, and unintended influence over unrelated tasks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.