ClawHub

Douyin Video Publisher

Security checks across malware telemetry and agentic risk

Overview

This skill appears intended for Douyin publishing, but it gives an agent real account-posting power with persistent login cookies and limited safety controls.

Install only if you trust the referenced Douyin MCP server and are comfortable letting an agent use your Douyin session to publish content. Use a dedicated creator account where possible, pin or review the external MCP server, protect or delete the saved cookie file when not needed, and require a final confirmation step before any upload or publish action.

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
93% confidence
Finding
The skill is explicitly designed to automate login and publish videos to a real Douyin account, which is an external side-effect with reputational and account-level consequences. Although the behavior is described functionally, the documentation does not prominently warn users that invoking the skill can cause immediate posting under their account, increasing the risk of unintended publication.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill documents persistent cookie storage for maintaining login state but does not explain that these cookies may grant continued access to the user's Douyin session if read by other local processes or users. Storing session artifacts on disk without a clear security warning can expose account takeover or unauthorized posting risk, especially on shared or compromised systems.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal