ClawHub

Xiaohongshu Copy

Security checks across malware telemetry and agentic risk

Overview

This skill drafts Xiaohongshu marketing posts using public trend searches, with no executable code, account access, posting authority, or persistence found.

Safe to install for Xiaohongshu copywriting. Review generated posts before publishing, and avoid giving confidential campaign or brand details unless you are comfortable with them being used to shape trend-search queries.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger conditions are broad enough to activate on casual mentions of '小红书文案' or '小红书笔记' rather than a clear request to invoke the skill. This can cause unintended routing, unnecessary web searches, and generation of platform-specific content the user did not explicitly ask for, which is a real security and safety boundary issue in agent systems.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The skill is defined entirely around Chinese-language output without indicating that language should follow user preference or be confirmed first. While not directly exploitable like code execution, this can override user intent, degrade reliability, and create unexpected behavior when the surrounding system expects language adaptation based on the user's request.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal