Descript Text To Video

• Outcome: Review
• Latest audit: May 29, 2026 at 9:35 PM UTC
• Version:
  1.0.0

Overview

This video-generation skill is mostly purpose-aligned, but it can connect to a third-party service and use or create credentials before the user clearly consents.

Install only if you are comfortable sending scripts, uploaded files, prompts, and project state to the NemoVideo backend for cloud processing. Avoid sensitive or proprietary material unless you have approved that transfer, and check whether NEMO_TOKEN is tied to an account or paid credits before use.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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 (4)

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The invocation guidance says to start on broadly phrased requests like sharing a script or even vague ideation, which can overlap with normal conversation and cause the skill to activate without a clear, informed user choice. In this skill, unintended activation is more concerning because activation leads to backend connection setup and potential transmission of user content to a remote service.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The example triggers are highly generic phrases like 'convert my text script' and 'export 1080p MP4', which are common requests that could refer to many tools or ordinary assistant tasks. Because this skill also initiates remote API use and cloud processing, ambiguous routing can result in user data being sent off-device without sufficiently specific consent.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The skill encourages users to drop scripts into chat and emphasizes cloud GPU processing, but it does not clearly warn users that their prompts and uploaded files will be transmitted to a third-party remote service. This is dangerous because users may share sensitive or proprietary documents under the assumption that processing is local or first-party, leading to confidentiality and privacy exposure.

Missing User Warnings

Medium

• Confidence: 98% confidence
• Finding: The skill silently uses an environment credential if present or automatically provisions an anonymous token otherwise, without clearly informing the user. That creates hidden authentication behavior and can cause users to unknowingly consume personal/account credits or create a third-party account linkage/session in the background.

VirusTotal

66/66 vendors flagged this skill as clean.