Douyin Send DM

• Outcome: Review
• Latest audit: Jun 12, 2026 at 12:54 PM UTC
• Version:
  0.1.0

Overview

The skill appears to perform its stated Douyin messaging purpose, but its activation wording is too broad for sending messages from a user's authenticated account.

Review this skill before installing. Only use it if you are comfortable with it operating your Douyin account, and require explicit confirmation of the recipient and exact message text before any DM is sent.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (2)

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The trigger text is intentionally broad enough that ordinary phrasing like 'tell @xyz hi' can activate a real-world messaging action. Because this skill sends messages through the user's authenticated browser session, overbroad activation increases the chance of unintended outbound communication or acting without sufficiently explicit user confirmation.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The condition 'Douyin / 私信 / 发私信 mentioned alongside a target user' is ambiguous and can match discussion, planning, or references rather than a direct command to act. In this skill's context, ambiguity is more dangerous because the resulting action is an authenticated communication on behalf of the user, which can cause privacy, reputational, or consent issues.

VirusTotal

64/64 vendors flagged this skill as clean.