Free Text Ai
PassAudited by ClawScan on May 10, 2026.
Overview
This instruction-only text-to-video skill appears coherent, but it sends prompts and uploaded files to a remote NemoVideo API using a bearer token.
This skill is reasonable for cloud text-to-video generation. Install it only if you are comfortable sending your prompts, documents, media, and URLs to the NemoVideo backend, and avoid uploading sensitive content unless you have reviewed the provider's terms and privacy practices.
Findings (3)
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.
Requests, uploads, credits, and render jobs may be tied to the token or anonymous session used by the skill.
The skill uses a bearer token for the NemoVideo backend, or creates an anonymous token if one is not present. This is expected for the service integration and is declared, but it is still delegated account/session authority.
If `NEMO_TOKEN` is in the environment, use it directly ... Otherwise, acquire a free starter token ... Include `Authorization: Bearer <NEMO_TOKEN>`
Use a token you can revoke, avoid sharing it in chat, and monitor any credits or account activity associated with the service.
Text, documents, media, or URLs supplied to the skill may be processed on NemoVideo servers rather than staying local.
The skill sends user prompts, uploaded files, URLs, and session data to an external provider. That is central to cloud video generation, but the artifact does not define privacy, retention, or data-handling limits.
API base: `https://mega-api-prod.nemovideo.ai` ... Upload: POST `/api/upload-video/nemo_agent/me/<sid>` — file: multipart `-F "files=@/path"`, or URL
Do not upload confidential, regulated, or secret material unless you are comfortable with the provider receiving and processing it.
The remote backend can influence edits, state queries, and export workflow steps within the current video session.
The skill allows backend SSE/GUI-style responses to drive additional API calls inside the NemoVideo workflow. This appears purpose-aligned, but it means some workflow actions may happen without detailed chat-visible steps.
The backend responds as if there's a visual interface. Map its instructions to API calls: - "click" ... → execute the action via the relevant endpoint ... Tool calls stay internal.
Review the timeline summary and final export before using or publishing the generated video, and ask for confirmation before any costly or irreversible action.