Caption Generator Davinci
PassAudited by ClawScan on May 3, 2026.
Overview
This skill appears to match its stated purpose, but it sends videos and prompts to a third-party NemoVideo cloud API and uses or creates a service token.
This looks purpose-aligned for cloud video captioning. Before installing, make sure you are comfortable sending your video files to mega-api-prod.nemovideo.ai and using or generating a NEMO_TOKEN. Avoid uploading sensitive footage unless you trust the provider.
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.
The service may perform edit/export steps based on backend responses during a session.
The skill instructs the agent to translate backend GUI-style responses into API actions. This is coherent with a cloud editor workflow, but it means the remote backend can influence the sequence of video-editing actions.
Backend says | You do ... "click [button]" / "点击" | Execute via API ... "Export button" / "导出" | Execute export workflow
Use the skill for intended video-captioning tasks and review outputs before relying on or sharing the rendered video.
The token controls access to the user’s NemoVideo session, credits, and render jobs.
The skill uses or obtains a Bearer token for the NemoVideo service. This is expected for the cloud API, and the instructions also say not to print tokens.
**Token**: If `NEMO_TOKEN` environment variable is already set, use it ... **Free token**: Generate a UUID ... POST to `https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token` ... `data.token` becomes your NEMO_TOKEN
Only provide or generate a NEMO_TOKEN if you trust the provider, and avoid sharing the token in chat or logs.
Users have less information for independently verifying who operates the skill or service.
The registry does not identify a source repository or homepage. There is no local code or install script shown, so this is a provenance note rather than a behavior concern.
Source: unknown Homepage: none
Prefer using this skill only if you are comfortable trusting the listed owner and the NemoVideo API endpoint.
Uploaded videos, prompts, and render-session data may be processed by the third-party cloud service.
The skill sends uploaded media and session messages to an external cloud API for processing. That is central to the stated purpose but involves transferring user video content outside the local environment.
**API base**: `https://mega-api-prod.nemovideo.ai` ... **Upload**: POST `/api/upload-video/nemo_agent/me/<sid>` — file: multipart `-F "files=@/path"`
Do not upload confidential or regulated videos unless you trust the provider’s handling of that data.