Tiktok Ai Subtitle Generator

• Outcome: Pass
• Latest audit: May 29, 2026, 8:37 PM
• Version:
  1.0.0

Overview

This is a cloud-based TikTok subtitle/video rendering skill, and its third-party upload, token, session, and export behavior is broadly aligned with that purpose.

Install only if you are comfortable sending TikTok clips, prompts, and related session metadata to nemovideo.ai for cloud processing. Avoid private, regulated, or unreleased media unless you trust the provider's privacy and retention practices, and use a limited or anonymous token where possible.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (4)

Description-Behavior Mismatch

Medium

• Confidence: 90% confidence
• Finding: The skill is presented as a subtitle generator, but the documentation exposes a much broader cloud editing and rendering pipeline, including session state inspection, arbitrary edit routing, export orchestration, and generalized media handling. This scope expansion increases the chance that user requests or agent behavior exceed user expectations and creates privacy and misuse risks because uploaded media and editing instructions are sent to a third-party service with persistent session state.

Context-Inappropriate Capability

Medium

• Confidence: 88% confidence
• Finding: The skill contains logic for anonymous token acquisition, session creation, and credit-aware account handling beyond a simple local subtitle tool. This is risky because it silently provisions third-party access and manages service-side identity/session state, which can surprise users, expose usage metadata, and normalize hidden account-like interactions without clear consent.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: Routing 'everything else' to the SSE backend makes the skill overly broad and allows nearly any unmatched prompt to be forwarded to a remote service. In context, this is more dangerous because the backend appears capable of generalized editing actions and stateful session manipulation, so unrelated or sensitive user content could be transmitted off-platform without a clear boundary.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill does not clearly warn users that their media files and editing instructions are uploaded to and processed by a third-party cloud service. Because the skill handles personal video content, the lack of an upfront disclosure materially increases privacy risk and reduces informed consent, especially for sensitive or copyrighted media.

VirusTotal

66/66 vendors flagged this skill as clean.