Text And Video
ReviewAudited by ClawScan on Apr 30, 2026.
Overview
This instruction-only skill appears aligned with cloud text-to-video creation, but it sends user text and media to a NemoVideo backend using a token-based session.
Before installing, make sure you are comfortable sending your text, documents, videos, and generated media to NemoVideo's cloud service. Use a dedicated NEMO_TOKEN if possible, avoid confidential uploads, and confirm any credit, registration, or export-plan limits.
Findings (8)
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 remote service response may cause the agent to make additional video-service API calls within the session.
The external backend can influence the agent's next API actions by returning GUI-like instructions. This is purpose-aligned for the service, but users should know backend responses steer the workflow.
The backend responds as if there's a visual interface. Map its instructions to API calls: - "click" or "点击" → execute the action via the relevant endpoint
Keep use limited to the intended NemoVideo workflow and review important actions like upload and export before proceeding.
Files or URLs supplied for video creation will be sent to the NemoVideo cloud backend.
The skill instructs the agent to upload local files or URLs to a remote video service. This is expected for text/video generation, but it is a sensitive tool operation.
Upload: POST `/api/upload-video/nemo_agent/me/<sid>` — file: multipart `-F "files=@/path"`, or URL: `{"urls":["<url>"],"source_type":"url"}`Only provide files and URLs you intend to upload to this third-party service.
Video jobs and uploads are tied to the NemoVideo token or anonymous identity used by the skill.
The skill uses a NemoVideo bearer token or creates an anonymous token for service access. The credential requirement is disclosed and aligned with the cloud backend.
Token check: Look for `NEMO_TOKEN` in the environment. If found, skip to session creation. Otherwise: ... POST `https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token`
Use a dedicated token if possible and avoid sharing or exposing the token outside this workflow.
Users have less publisher and service provenance information to review before trusting the cloud workflow.
The skill has no known source or homepage in the provided metadata, while it depends on an external cloud API. This is a provenance gap, not direct evidence of malicious behavior.
Source: unknown; Homepage: none
Verify the provider and service terms before sending important or sensitive content.
Your text, uploaded media, drafts, and generated outputs may be stored or processed in the remote NemoVideo session.
User prompts and media are processed remotely, and the skill also queries session state containing drafts and generated media. This is expected for the service but involves sensitive content handling.
Send me your text and video and describe the result you want. The text-to-video creation runs on remote GPU nodes
Do not upload private, confidential, or regulated content unless you are comfortable with NemoVideo processing it.
Your instructions are sent to a remote agent-like backend that may generate responses and drive the video workflow.
The skill communicates with a remote `nemo_agent` over SSE using a bearer-authenticated session. This is disclosed and purpose-aligned, but it is a third-party agent/provider boundary.
Send message (SSE): POST `/run_sse` — body `{"app_name":"nemo_agent","user_id":"me","session_id":"<sid>","new_message":{"parts":[{"text":"<msg>"}]}}`Treat the backend as an external service and avoid sending content you would not share with that provider.
A started render may continue remotely even if you leave before it finishes.
Remote render jobs can continue or become orphaned if the client session ends before completion. This is disclosed and consistent with cloud rendering, but it affects job containment.
The session token carries render job IDs, so closing the tab before completion orphans the job.
Start exports only when you intend to wait for completion, and check job status if you reconnect.
You may need registration or an upgraded plan to export even if credits are available.
The export language may be confusing because it says export is free/no credits while also documenting a plan-based export block. The tradeoff is disclosed, but users should notice it.
**Export** (free, no credits) ... 402 | Free plan export blocked | Subscription tier issue, NOT credits. "Register or upgrade your plan to unlock export."
Confirm pricing, credit, and export limits before relying on the skill for finished videos.