ClawHub
Back to skill

Security audit

Design System Audit

Security checks for vulnerabilities and agentic risk

Overview

This is a plain design-system audit template with no code execution, persistence, or hidden security-impacting behavior.

Install this only when you are comfortable letting the agent review the design-system materials you provide or explicitly authorize, such as component documentation, Storybook/code examples, Figma exports, or adoption feedback. I found no hidden execution or persistence behavior.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 216)May include surrounding context.

md
## Anti-Patterns

- [ ] Do not assess only the Figma library without checking the code implementation — Figma-code drift is one of the most common and costly design system failures
- [ ] Do not score adoption without interviewing teams — audit tool metrics miss the human reasons teams build custom components instead of using the system
- [ ] Do not treat all component gaps equally — prioritise gaps based on how many production screens rely on custom implementations, not alphabetically
- [ ] Do not recommend adding more components without first auditing documentation quality — an undocumented component is often worse than no component

Static analysis

No suspicious patterns detected.