ClawHub
Back to skill

Security audit

Xiaohongshu Publish

Security checks for vulnerabilities and agentic risk

Overview

The skill’s Xiaohongshu publishing workflow is mostly coherent, but it asks users to keep active account cookies in a work directory and run a persistent local publishing service without enough security guidance.

Install only if you are comfortable running third-party Xiaohongshu automation locally. Treat cookies.json like a password: keep it outside shared project folders, restrict permissions, delete or rotate it after use, and avoid leaving the MCP service running when you are not publishing. Review content carefully before confirming publish because the skill notes that posted notes cannot be edited or deleted through the MCP workflow.

SkillSpector

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 (1)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly instructs users to generate and persist `cookies.json` containing active Xiaohongshu login state in the working directory, but it does not warn that these cookies are sensitive credentials that can enable account takeover if copied. Because the workflow also requires long-lived reuse of those cookies by a local MCP service, the exposure window is extended and accidental leakage through backups, shared folders, or other tools becomes more likely.

Static analysis

No suspicious patterns detected.