Tiktok Bulk Publisher Test

Security checks across malware telemetry and agentic risk

Overview

This appears to be a real TikTok publishing helper, but it can publish videos publicly with account credentials and has limited safeguards before posting.

Install only if you intend to let this skill publish to a TikTok account. Use a test account or SELF_ONLY privacy first, review every video/title/privacy setting before running bulk jobs, and provide only least-privilege TikTok tokens you are comfortable using for live posting.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Intent-Code Divergence

Medium

Confidence: 94% confidence
Finding: The OAuth helper hardcodes the scope string to `video.publish,user.info.basic` even though the module documentation says only `video.publish` is required. Requesting broader permissions than necessary violates least-privilege and can expose additional user profile data if the token is later misused or leaked.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The README explicitly markets bulk upload and publishing to TikTok but does not clearly warn that using the skill will perform external actions on a third-party account and change user-visible account state. This can lead to accidental posting, reputational harm, or misuse by users who do not realize the tool has live publishing capability, especially because the skill automates batch operations.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The skill clearly facilitates uploading local video files and associated metadata to TikTok, but the documentation does not explicitly warn users that content leaves the local environment and is sent to a third-party platform. This can lead to inadvertent disclosure of sensitive media, captions, or account-linked information, especially in automated or batch workflows where users may assume processing is local.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal