Dataify YouTube Audio By URL

• Outcome: Review
• Latest audit: Jul 16, 2026 · 8:44 PM UTC
• Version: 1.2.0

Overview

This skill appears purpose-built for submitting Dataify YouTube audio tasks, but it can implicitly invoke a credentialed external request using a saved token, so it belongs in Review rather than automatic approval.

Install only if you expect your agent to submit YouTube audio collection jobs to Dataify. Keep DATAIFY_API_TOKEN scoped to Dataify, monitor quota/usage, and prefer explicitly invoking this skill or confirming the target URL and token use before any task is submitted.

SkillSpector

By NVIDIA

Vulnerability Patterns

• 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
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (5)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 89% confidence
• Finding: The skill instructs the agent to read a locally saved API token from the environment and make outbound network requests, but there is no declared permissions model or user-visible authorization boundary described. That creates a capability mismatch where sensitive local secrets and network access may be used implicitly, increasing the risk of unintended token use or data exfiltration through the remote service.

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: The activation description is very broad and includes catch-all phrases like general scraping/collection wording and troubleshooting/token handling, which can cause the skill to trigger on loosely related requests. Overbroad activation increases the chance that the agent invokes a networked, credential-using skill in contexts the user did not clearly intend, leading to accidental external requests or secret usage.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The skill description contains very broad trigger phrases, including generic terms like audio collection/scraping and troubleshooting/token handling, which can overlap with ordinary user requests. This can cause the wrong skill to activate and initiate or guide external data-collection actions for YouTube URLs when the user did not specifically intend to use this Dataify workflow.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The skill enables allow_implicit_invocation without any visible narrowing constraints in this file, which means the agent may auto-select and invoke an external action based on loose semantic matching rather than explicit user confirmation. Because this skill submits Dataify tasks for YouTube audio collection by URL, unintended invocation could trigger third-party requests, consume API quota, or process user-supplied targets without sufficiently clear consent.

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.