Generator Video
ReviewAudited by ClawScan on Apr 30, 2026.
Overview
This instruction-only video skill appears purpose-aligned, but using it sends prompts or media to a Nemovideo cloud API and uses a NEMO_TOKEN credential and render credits.
Before using this skill, make sure you are comfortable sending prompts, clips, images, and audio to Nemovideo's cloud service and using a NEMO_TOKEN or anonymous token with credits. Avoid sensitive media, keep tokens private, and deliberately confirm export/download requests because they may create cloud render jobs or consume credits.
Findings (7)
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.
The remote service may guide the agent through video-editing steps after the user starts a generation or edit task.
Remote backend responses can influence the agent's next API actions. This is expected for this hosted video workflow, but users should know the provider's responses are operationally important.
The backend responds as if there's a visual interface. Map its instructions to API calls
Use the skill only for its intended video tasks and review important actions such as uploads and exports.
A prompt, clip, image, or audio file you provide may be sent to the cloud service, and exports may use credits or create render jobs.
The skill can upload user files or URLs and start cloud render/export jobs. These actions fit the stated video-generation purpose, but they can expose media and consume service resources or credits.
`/api/upload-video/nemo_agent/me/<sid>` | POST | Upload a file (multipart) or URL. ... `/api/render/proxy/lambda` | POST | Start export.
Avoid uploading sensitive media, and confirm you intend to export before asking for downloads or final renders.
Anyone with access to the token could potentially use the associated Nemovideo session or credits.
The skill creates or uses a bearer token for the provider service. This is disclosed and purpose-aligned, but the token represents account/session authority and credits.
Free token: Generate a UUID as client identifier, then POST to `https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token` ... `data.token` becomes your NEMO_TOKEN (100 credits, 7-day expiry).
Keep NEMO_TOKEN private, do not paste it into chats or logs, and use a dedicated token if possible.
Changes or issues in the remote service could affect uploads, editing behavior, exports, or privacy handling.
The skill depends on an external hosted API whose server-side implementation is not included in the artifact. This is normal for a cloud rendering skill, but users must trust that provider.
Base URL: `https://mega-api-prod.nemovideo.ai`
Use the skill only if you trust the Nemovideo service and are comfortable with a cloud-rendering dependency.
Your project state may remain associated with a cloud session while generation or export is in progress.
The workflow stores and reuses cloud session/render context. This is necessary for video rendering, but prompts, media state, and job IDs may persist in the provider session.
Save `session_id` from the response. ... The session token carries render job IDs, so closing the tab before completion orphans the job.
Do not use sensitive or confidential prompts/media unless you are comfortable with them being processed and retained in the cloud session.
User prompts and editing instructions can be sent to the provider, and internal backend tool activity may not be shown verbatim.
The local agent exchanges user messages and backend tool results with the remote `nemo_agent` service. The endpoint is fixed and purpose-aligned, but the boundary between local assistant and remote agent is important for privacy.
`/run_sse` | POST | Send a user message. Body includes `app_name`, `session_id`, `new_message`. Stream response with `Accept: text/event-stream`. ... Tool call/result | Process internally, don't forward
Assume video instructions and related project context are shared with the Nemovideo backend.
Interrupted exports may leave unfinished or hard-to-track cloud jobs.
Render work can continue in the cloud and become disconnected from the local session if interrupted. This is contained to rendering, but it can affect job tracking or credits.
Each export job queues on a cloud GPU node ... closing the tab before completion orphans the job.
Keep the session open until exports complete and check credits/status if a render is interrupted.