ClawHub
Back to skill

Security audit

xiaohongshu-post-generator

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed remote social-media post generator, with expected external API use and shareable output links but no hidden local access or unsafe installation behavior.

Install only if you are comfortable sending prompts, uploaded/reference images, and generated post data to the DeepNLP/Craftsman service. Avoid regulated, confidential, or private material unless you have reviewed that service's privacy and sharing controls, and treat generated share URLs as potentially accessible links.

SkillSpector

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

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The skill explicitly instructs users to send prompts, uploaded images, and an API-key-authenticated request to external services, but provides no privacy or data-handling warning. This can lead users to disclose sensitive content or proprietary images to third-party infrastructure without informed consent, especially in an agent ecosystem where users may assume local-only processing.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The documentation promotes export, publishing, workspace access, and share URLs without warning that generated assets and embedded user content may be accessible through persistent links or stored in remote workspaces. This increases the chance of accidental exposure of private drafts, internal marketing materials, or copyrighted/sensitive images if users treat the workspace as private by default.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.