AI 衣橱搭配

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:19 PM UTC
• Version:
  0.9.1

Overview

This skill coherently generates outfit images through a declared AI Closet API, with disclosed local script execution, image handling, and preview/upload side effects users should understand.

Install only if you trust the AI Closet endpoint and are comfortable sending a dedicated API key plus outfit context such as city, date, and style to that service. Expect the skill to run a local Python script, use ImageMagick from your PATH, save images in a temp folder, auto-open the generated image on desktop systems, and allow OpenClaw to upload the generated image in supported chat channels.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (5)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 91% confidence
• Finding: The skill explicitly instructs the agent to read environment configuration, execute a local Python script via shell, access the network API, and handle local files/images, yet it declares no permissions. This creates a transparency and policy gap: users and the runtime may not understand the skill's real capabilities, increasing the chance of unauthorized command execution or data handling without informed consent.

Context-Inappropriate Capability

Medium

• Confidence: 84% confidence
• Finding: The skill automatically opens a local GUI application after generating output, which exceeds the stated purpose of generating and returning outfit recommendations for CLI/IM channels. In agent or server contexts, unexpected local application launches can create unsafe side effects, leak operational context to the desktop session, or disrupt automated environments.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The trigger phrases include very common expressions such as '今天穿什么', '穿搭', and 'outfit', which are broad enough to match ordinary conversation. Overbroad activation can cause the skill to run unexpectedly, leading to unintended external API calls, local script execution, and image downloads based on casual user text.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill description says it will generate outfit recommendations, but it does not clearly warn that user-derived inputs such as date, city, weather/style preferences will be sent to an external API endpoint and that remote images will be downloaded. This lack of disclosure undermines informed consent and can expose user context or metadata to third parties unexpectedly.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The workflow requires automatic execution of a local shell command and states that the script will open a system preview window, but this behavior is not surfaced as a clear warning to the user. Unexpected local command execution and UI launching can be abused for surprise actions, disrupt the user environment, or erode trust even if the intended function is benign.

VirusTotal

66/66 vendors flagged this skill as clean.