Back to skill

Security audit

Ux Architect

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent UX architecture helper with no install commands, executables, network behavior, credential access, or hidden persistence.

This is appropriate to install if you want an agent to help plan UX foundations, CSS systems, layout structure, and developer handoff docs. Be aware that its activation wording is broad, so users who want tighter control should invoke it explicitly by name and limit any project-file review to relevant local specification files.

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
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
93% confidence
Finding

The activation guidance says to reference the agent "by name or specialty when you need its expertise," but does not define specific trigger phrases, scope boundaries, or exclusion conditions. Terms like "specialty" and "need its expertise" are broad enough to overlap with ordinary discussion about UX or architecture, increasing the chance of unintended invocation.

Content

No source excerpt is available for this finding.