Dataify YouTube Product By ID

• Outcome: Pass
• Latest audit: Jul 16, 2026 · 8:45 PM UTC
• Version: 1.2.0

Overview

This appears to be a legitimate Dataify helper for submitting YouTube video information collection tasks, with a notable but disclosed reliance on a saved Dataify API token.

Install only if you are comfortable with an agent using DATAIFY_API_TOKEN from your environment to submit Dataify jobs. Review parameters before confirming a run, and avoid saving the token persistently unless you want future sessions to reuse it.

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 Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (6)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 93% confidence
• Finding: The skill instructs the agent to access a saved environment token and make outbound network requests, but no explicit permissions are declared. That mismatch weakens user visibility and platform enforcement, creating a risk of silent credential use and external data submission beyond what a user may expect from the skill metadata.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The trigger description is extremely broad and includes ambiguous phrases like 'similar' wording and troubleshooting/token-handling cases, which can cause the skill to activate for requests the user did not intend for this external service. In this context, unintended invocation is more dangerous because the skill can use local credentials and submit network requests to a third-party API.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The trigger description is unusually broad and includes many generic phrasing variants, which increases the chance the skill is invoked when the user did not clearly intend to submit a Dataify scraping task. In this context, accidental invocation can lead to unintended external requests, confusing credential prompts, or use of defaults such as a sample `video_id`, making the issue a real safety and privacy concern even though it does not directly enable code execution.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The skill instructs the agent to automatically check for and reuse a locally stored `DATAIFY_API_TOKEN` without first clearly informing the user that an existing credential may be accessed and used on their behalf. This can cause silent credential use, cross-session privacy surprises, and unauthorized third-party API activity if the current user did not expect stored secrets to be reused.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The skill enables implicit invocation while advertising a broad natural-language use case, which increases the chance the agent will trigger this external task submission flow from ambiguous user input. Because the action submits Dataify jobs and may consume API-backed resources or send user-supplied video IDs to a third party, unintended invocation can cause unauthorized external requests, cost, or data handling outside the user's clear intent.

Autonomous Decision Making

Medium

• Category: Excessive Agency

Content

- If the user provides a token in the request, use it for this run.
- If no token is provided, first check whether `DATAIFY_API_TOKEN` is already saved locally in the environment.
- If `DATAIFY_API_TOKEN` is saved locally, use it without asking the user to re-enter the token.
- If no token is available locally, tell the user they need to provide a Dataify API TOKEN.
- If the user does not have an API TOKEN, tell them they can register or log in at [Dataify](https://dashboard.dataify.com/login?utm_source=skill) to get one.
- If the user already has an API TOKEN, tell them it is available in the top-right area of [Dataify](https://dashboard.dataify.com?utm_source=skill).

• Confidence: 91% confidence
• Finding: without asking

VirusTotal

65/65 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.