ClawHub
Back to skill

Security audit

UIUX设计助手(免费版)

Security checks for vulnerabilities and agentic risk

Overview

This UI/UX helper is mostly a Markdown design-advice skill, but it asks for shell and write access and describes state-changing operations that are broader than its stated purpose.

Review this skill before installing. It does not contain executable code or obvious malicious behavior, but you should only grant write or shell access when you explicitly want it to edit project files or run commands, and prefer using it for in-chat design guidance unless the publisher narrows the permissions and file-operation rules.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill is presented as a conversational UI/UX advisory tool, but its manifest and documentation also expose operational behaviors such as create/query/modify/delete/save/import/export. This capability mismatch can mislead users and host agents into granting broader file or command privileges than the task requires, increasing the chance of unintended local actions or abuse through prompt-driven workflows.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

Declaring exec for a basic UI/UX guidance skill violates least privilege. Even without explicit malicious commands in the file, shell execution materially raises the risk that the skill could be induced to run local commands, inspect the environment, alter files, or chain into broader system actions unrelated to design advice.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The documentation contains inconsistent trust signals: it claims no extra scripts or external APIs are needed and that generation is local, yet elsewhere depends on exec capability and references network-related troubleshooting. These contradictions can hide the real operational footprint of the skill, preventing users and reviewers from accurately assessing what permissions and behaviors are involved.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The markdown advertises modify/delete/save/import/reset/export-style operations without warning about consequences to local files or requiring confirmation. In a skill with write/exec capabilities, this omission makes unsafe file changes more likely, especially if the user expects only design suggestions rather than state-changing actions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The '触发条件' section contains only a fragment ('、品牌视觉时使用。不适用于非本工具能力范围的需求.') and does not provide specific invocation phrases, scope boundaries, or clear positive/negative examples. This makes activation overly ambiguous for a markdown skill description and could cause unintended invocation in loosely related design conversations.

Content

No source excerpt is available for this finding.