Ai Generator Video
PassAudited by VirusTotal on May 4, 2026.
Overview
Type: OpenClaw Skill Name: ai-generator-video Version: 1.0.0 The skill bundle provides a legitimate interface for an AI agent to interact with the NemoVideo AI video generation service (mega-api-prod.nemovideo.ai). It includes detailed instructions for session management, anonymous authentication, file uploads, and polling for video render status. The requested permissions (NEMO_TOKEN and ~/.config/nemovideo/) are strictly relevant to the skill's stated purpose, and no indicators of data exfiltration, malicious execution, or harmful prompt injection were found.
Findings (0)
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.
When invoked for video creation, the agent may start remote processing jobs and exports, which may use service credits or plan limits.
The skill directs the agent to call remote API endpoints and start generation/export workflows as part of normal use. This is disclosed and central to the video-generation purpose.
On first interaction, connect to the processing API before doing anything else... `/run_sse` | POST | Send a user message... `/api/render/proxy/lambda` | POST | Start export.
Use the skill only for intended video-generation tasks and review export or credit-related actions before proceeding.
The token can authorize video-generation sessions or credit usage for the associated NemoVideo account or anonymous client.
The skill uses a bearer token or generated anonymous token to authenticate with the NemoVideo API. This is expected for the service, and the artifact also says not to print tokens.
If `NEMO_TOKEN` environment variable is already set, use it... Free token: Generate a UUID as client identifier, then POST... The response field `data.token` becomes your NEMO_TOKEN... Include `Authorization: Bearer <NEMO_TOKEN>`.
Use a token intended for this service, avoid sharing it in prompts or logs, and rotate/revoke it if exposed.
Private brand photos, product descriptions, audio, or video files may leave the local environment and be processed by a third-party service.
The documented workflow sends user prompts, images, videos, audio, or URLs to an external NemoVideo API for processing.
Send me your text or images... The AI video creation runs on remote GPU nodes... `/api/upload-video/nemo_agent/me/<sid>` | POST | Upload a file (multipart) or URL.
Upload only content you are comfortable sending to the external provider, and review the provider’s privacy and retention terms for sensitive materials.