ClawHub
Back to skill

Security audit

ui-designer

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent UI design workflow skill that may use references/search and create design files, with no hidden code, privilege escalation, or malicious behavior found.

Reasonable to install for UI design work. Before using it with confidential projects, avoid private URLs or proprietary details unless you are comfortable with reference analysis or web search, and check the output directory for existing files before generating deliverables.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrases are broad enough to activate on routine requests like general design help or discussing an idea, which can cause the agent to enter a multi-step workflow and use tools the user did not explicitly request. In context, this increases the chance of unexpected web lookups, URL analysis, or file generation, creating consent and scope-creep risks rather than direct code-execution risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill permits analysis of user-provided URLs and web searching via external services without an explicit privacy notice explaining that user inputs, URLs, or derived queries may be sent to third parties. In this design-assistance context, users may share proprietary product ideas or internal URLs, so silent external transmission increases confidentiality risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill directs the agent to save multiple artifacts into workspace paths without first requiring a clear user-facing notice or confirmation that files will be created or overwritten. This can lead to unexpected persistent changes in the working environment, accidental overwrites, and confusion about what data was stored.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The manifest-style description is entirely in Chinese and frames the skill's behavior in that language, with the rest of the operational guidance also presented only in Chinese. There is no indication that the user can choose another language or that the locale restriction is justified as region-specific.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.