Back to skill

Security audit

Design System

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local design-system helper that stores design preferences in a disclosed local folder and does not include code, network calls, or hidden high-impact behavior.

Before installing, be aware that the skill will keep durable local notes about your design system, stack, platforms, team context, constraints, and preferences under ~/design-system/. Avoid putting secrets or sensitive business details there, and review or delete that folder if you no longer want the saved context.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The activation guidance is broad enough to trigger the skill whenever the user is doing general UI or component work, which can cause the agent to invoke the skill outside the user's explicit intent. In practice, this increases the chance of unexpected behavior, unnecessary persistence, and accidental application of design-system rules in unrelated conversations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs the agent to store user preferences and team/context details in a local memory file without first informing the user that this information will be persisted. This creates a privacy and consent issue because users may reveal workflow, team, or platform details assuming they are only part of the current conversation, not durable storage.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.