CP skill test 123456

• Outcome: Review
• Latest audit: May 29, 2026 at 9:22 PM UTC
• Version:
  1.0.0

Overview

This skill appears intended to publish to Xiaohongshu, but its trigger scope and publish flow make accidental public posting too easy.

Review before installing. Use this only if you are comfortable letting an agent operate a logged-in Xiaohongshu publishing session, and require a manual review plus an explicit final confirmation before anything is posted publicly.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (2)

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The trigger phrases include broad everyday expressions such as “写一篇小红书”, which can match normal content-generation requests rather than an explicit request to publish. In a skill that performs real posting actions, ambiguous invocation increases the risk of accidental activation and unintended publication to a live account.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The skill performs a real-world side effect—posting content publicly—but the instructions do not require an explicit user warning, review, or final confirmation immediately before clicking “发布”. This makes accidental or unauthorized publication more likely, especially when combined with broad triggers and browser automation.

VirusTotal

66/66 vendors flagged this skill as clean.