ClawHub
Back to skill

Security audit

xiaohongshu-title

Security checks across malware telemetry and agentic risk

Overview

This is a focused Xiaohongshu title-writing skill with no evidence of hidden system access, data collection, persistence, or unsafe execution.

Install this if you want Xiaohongshu/RedNote-style marketing title drafts. Review generated titles before publishing, especially urgency, beauty, health, finance, or results-based claims, and specify your preferred language or tone if you do not want emotional platform-native copy.

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
89% confidence
Finding
The trigger condition accepts essentially any raw text or topic, which makes the skill eligible to activate on very broad user inputs without clear scoping or opt-in. In an agent environment, this can cause inappropriate routing, style hijacking of unrelated tasks, or unintentional application of persuasive content-generation behavior where the user did not request it.

Natural-Language Policy Violations

Medium
Confidence
82% confidence
Finding
The skill hard-codes a specific emotional, native, non-'AI-speak' style as the default output standard without offering user choice. While not directly a security exploit, this reduces user control and can steer outputs toward manipulative or undesired persuasive framing, especially when combined with CTR-maximization goals.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.