xiaohongshu-search

• Outcome: Review
• Latest audit: May 29, 2026 at 9:27 PM UTC
• Version:
  1.0.0

Overview

This is a coherent Xiaohongshu research skill, but it asks an agent to control a logged-in Chrome session through remote debugging without enough containment guidance.

Install only if you are comfortable letting the agent control a Chrome session for Xiaohongshu research. Use a separate Chrome profile or test account, keep remote debugging local, close that browser when finished, and avoid using a profile with unrelated sensitive logins.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The invocation guidance is broad enough to encourage arbitrary searches based on free-form city/business keywords without clear scope, authorization, or data-handling limits. Because the skill operates a logged-in browser session against a live consumer platform, this can lead to overcollection, unintended browsing beyond the intended task, and use in contexts not originally approved by the user or organization.

VirusTotal

65/65 vendors flagged this skill as clean.