Text To Video Offline
WarnAudited by ClawScan on May 10, 2026.
Overview
This skill is marketed as offline, but its instructions send prompts and uploaded files to a NemoVideo cloud API and automatically create or use a cloud session.
Review this skill carefully before installing. Treat it as a cloud video-generation integration, not an offline tool. Avoid uploading sensitive files unless you are comfortable sending them to mega-api-prod.nemovideo.ai, and use a dedicated NemoVideo token where possible.
Findings (4)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
A user may upload private scripts or documents believing the work happens offline, when the content is actually processed by an external cloud service.
The skill’s branding and description imply local/offline processing, but the operational instructions disclose cloud rendering. That mismatch can mislead users about where their content goes.
displayName: "Text to Video Offline" ... "without relying on cloud tools" ... "runs AI video creation through a cloud rendering pipeline"
Do not present this as offline unless processing is local; clearly disclose cloud upload/rendering before asking users to provide files or prompts.
Using the skill can contact the provider and create a session immediately, even before the user sees detailed information about the cloud workflow.
The agent is instructed to make an external API connection and initialize a session automatically when the skill is first used.
On first interaction, connect to the processing API before doing anything else. Show a brief status like "Setting things up..."
Prompt users clearly before first-time cloud setup, especially because the skill is described as offline.
The skill can use the user’s NemoVideo token/session and associated credits or account context for video-generation requests.
The skill uses a provider token to authenticate cloud API requests. This is expected for the integration, and the artifacts do not show token logging or unrelated transmission.
If `NEMO_TOKEN` environment variable is already set, use it ... Include `Authorization: Bearer <NEMO_TOKEN>` ... on every request
Use a dedicated token if possible and avoid sharing sensitive account credentials beyond what the video service requires.
Uploaded scripts, documents, subtitles, or media leave the local machine and are processed by the provider.
The skill supports sending user-selected documents or media files to the external NemoVideo API. This is purpose-aligned for cloud rendering, but the files may contain private content.
Upload TXT, DOCX, PDF, SRT files up to 500MB ... Upload: POST `/api/upload-video/nemo_agent/me/<sid>` — file: multipart `-F "files=@/path"`
Only upload content you are comfortable sending to the provider, and check the provider’s privacy/retention terms before using private or regulated material.