ClawHub
Back to skill

Security audit

design

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent frontend design guidance skill with no evidence of hidden execution, credential access, persistence, or destructive behavior.

This skill is reasonable to install for frontend design help. It will strongly steer UI decisions toward mobile-first layout, accessibility checks, design tokens, and framework-specific component guidance, so review generated UI changes for fit with your product and existing codebase.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Hidden Instructions

High
Category
Prompt Injection
Content
</div>
      </div>
    </div>
    <!-- repeat for Pro and Enterprise -->
  </div>
</div>
```
Confidence
70% confidence
Finding
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Anti-Refusal Statement

High
Category
Anti-Refusal
Content
## Errors

- Say what happened and what to do next.
- Do not apologize. Do not blame the user.
- Be specific: "Enter a date after 2024-01-01" not "Invalid date."

## Empty States
Confidence
55% confidence
Finding
Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Excessive Permissions

Low
Category
Privilege Escalation
Content
- **Keyboard:** every action reachable, logical tab order, visible focus, skip links.
- **Touch:** targets ≥ 44x44px, no hover-only features, clear tap feedback.
- **Custom controls:** test the primary gesture, scroll across the control, and interrupt the drag with a second pointer or `pointercancel`.
- **Permissions:** read-only and no-access states are designed, not left to defaults.

## Verify
Confidence
80% confidence
Finding
Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.

Static analysis

No suspicious patterns detected.