ClawHub
Back to skill

Security audit

Douyin Browser Publish

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says, but it can publicly post to a logged-in Douyin account without a final confirmation step.

Install only if you intend to let an agent operate a logged-in Douyin creator session. Before allowing use, require a manual final check of the account, selected video, title, description, hashtags, visibility settings, and destination page; a safer version would stop at draft/upload or require an explicit confirmation before clicking publish.

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
95% confidence
Finding
The skill performs an irreversible public posting action by clicking the final publish button without requiring an explicit user confirmation immediately beforehand. In a browser automation context, this can cause unintended publication of content, reputational harm, or accidental disclosure if the title, description, or selected account are wrong.

Static analysis

No suspicious patterns detected.