ClawHub

XHS Daily Hot Content

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Xiaohongshu content-generation helper that searches trends and updates a local YAML post library, with some workflow-scope cautions but no hidden or high-impact behavior.

Install this if you want an agent to search the web and update templates/posts.yaml for daily Xiaohongshu content. If that YAML file is important, keep backups and ask the agent to preview generated posts before writing them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
95% confidence
Finding
The trigger phrases include very broad, everyday requests such as '更新文案', '每日文案', and '今天有什么热点可以写', which can cause the skill to activate when the user did not intend to run an automated workflow. In this skill, accidental activation is more dangerous because it can lead to network searches, bulk AI-generated content creation, and file modification without clear user confirmation.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill instructs the agent to read, modify, and rewrite templates/posts.yaml by prepending 10 generated entries, but it does not require explicit user consent, preview, backup, or rollback. In context, this increases risk because the action is state-changing, can overwrite formatting or content integrity, and may pollute a production content library with low-quality or irrelevant generated data.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal