UI Design System

• Outcome: Pass
• Latest audit: Sep 10, 2026 · 8:39 PM UTC
• Version: 1.0.0

Overview

This is a markdown-only UI/UX design guidance skill with no executable code or hidden privileged behavior.

Installers should know this skill may steer general design-related requests into a comprehensive design workflow. That is consistent with its stated purpose, but teams wanting tighter routing may prefer explicit invocation wording.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The README lists generic invocation phrases like "Design a landing page for [product]" and "Review this design for quality" without clarifying when this skill should activate versus other general design or review skills. There are no exclusion conditions, scope limits, or negative examples, which makes the trigger guidance overly broad for a markdown skill description.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The trigger phrase "Design a [type] page for [audience]" is broad and overlaps with ordinary conversational requests a user may make in many contexts. This can cause unintended skill activation and routing of requests into this skill's full multi-phase workflow even when the user did not explicitly intend to invoke it.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The phrase "Create a color system for [brand]" lacks scope constraints and is phrased like a common design request, making accidental activation likely. In agent environments, broad natural-language triggers can hijack unrelated conversations and cause the skill to take over tasks unexpectedly.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The trigger "Review this design" is especially generic and likely to appear in normal product, design, or QA discussions. Because it maps to an extensive rubric-driven evaluation flow, unintended activation could alter agent behavior, context selection, or output formatting without clear user consent.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The phrase "Build a design system" is a highly generic request commonly used in frontend, branding, and product conversations. Its breadth makes reliable activation difficult and increases the chance that this skill is invoked when the user intended a narrower or different task.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The trigger "Improve the typography" overlaps with common feedback given during UI reviews, content editing, and frontend implementation. In a shared agent environment, such broad phrasing can create prompt-routing ambiguity and unintended invocation of this skill's prescriptive methodology.