Tiktok Auto Reply

• Outcome: Review
• Latest audit: May 29, 2026 at 9:26 PM UTC
• Version:
  1.0.0

Overview

This skill is transparent about automating TikTok replies, but it can run unattended with TikTok credentials and its dry-run safety claim is not actually enforced in the code.

Review before installing. Use a test or least-privilege TikTok app, avoid broad comment.create access unless you truly need automated public replies, keep watch mode visible and stoppable, and do not rely on dryRun as a safety control unless the code is fixed to skip all reply calls when dryRun is true.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• 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 (2)

Intent-Code Divergence

Medium

• Confidence: 98% confidence
• Finding: The code prints that `dryRun=true` will prevent actual replies, but `dryRun` is never checked in `check()`, `watch()`, or `replyComment()`. In a skill designed to automate TikTok interactions, this mismatch can cause unintended live actions against user expectations, leading to unauthorized posting, account restrictions, or policy violations.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The skill documents collection of TikTok comments and use of API credentials, but it does not explain how comment data is handled, stored, transmitted, or protected. That omission can lead users to deploy the skill without safeguards for personal data or secrets, increasing the risk of credential leakage, unauthorized data retention, or noncompliant handling of user-generated content.

VirusTotal

65/65 vendors flagged this skill as clean.