ClawHub
Back to skill

Security audit

Xiaohongshu Copywriter

Security checks across malware telemetry and agentic risk

Overview

This is a Xiaohongshu copywriting prompt skill with documentation risks, but no hidden code, persistence, credential theft, or destructive behavior in the artifacts.

Safe to install as a prompt-only writing aid. Do not paste real API keys into chats, screenshots, issue reports, or shared logs, and use the viral-post feature only for high-level inspiration from content you own or have permission to reference. Verify any beta/Pro or distribution claims with the publisher before providing credentials.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The README instructs users to place an API key directly into a visible configuration command format but provides no guidance on secure storage, rotation, scope, or avoiding accidental disclosure. This can lead to credential leakage through shell history, screenshots, copied chats, or checked-in config files, especially since the key format is explicitly shown.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly promotes a 'viral post imitator' that analyzes existing Xiaohongshu posts and reuses their structure to generate new content, but it provides no safeguards around copyright, plagiarism, deceptive imitation, or platform terms. In this context, the omission can facilitate unauthorized derivative copying and policy-violating content reuse at scale, even if the feature is framed as marketing assistance rather than abuse.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
README.md:51