Douyin Video Publish

• Outcome: Review
• Latest audit: May 29, 2026 at 9:29 PM UTC
• Version:
  1.0.0

Overview

This skill is a real Douyin publishing automation, but it needs review because it can post publicly from a logged-in account without a clear final confirmation and always adds a fixed location.

Install only if you are comfortable letting an agent operate a logged-in Douyin creator session. Before use, require the agent to show the exact account, video, title, hashtags, cover, visibility settings, and location, and approve the final publish action explicitly; remove or change “苏州中心” unless you intentionally want that location attached.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The skill instructs the agent to click the final Douyin publish button on a live account and only verify afterward, but it does not require an explicit pre-action confirmation that the user is ready for an irreversible public post. In a browser automation context, this creates a real risk of accidental public publication, especially if metadata, audience, or content are incorrect at the moment of submission.

Natural-Language Policy Violations

Medium

• Confidence: 84% confidence
• Finding: The skill hard-codes the location to “苏州中心” without user input or justification, causing the agent to attach potentially false geolocation metadata to every published video. This can misrepresent the content, create compliance or trust issues, and expose the user to reputational harm if the posted location is inaccurate or unintended.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The trigger phrases are broad and overlap with common user intents such as '发抖音' and '发布抖音', which can cause the skill to activate when the user did not explicitly consent to browser automation and publishing. In this skill’s context, unintended invocation is more dangerous because the action can upload and publish content to a real social-media platform, creating reputational or privacy harm.

VirusTotal

65/65 vendors flagged this skill as clean.