Ai Karaoke Video

PassAudited by ClawScan on May 11, 2026.

Overview

This appears to be a cloud karaoke-video generator, but it sends selected media and prompts to an external NemoVideo API and uses a bearer token/credits.

This skill looks purpose-aligned for generating karaoke videos. Before using it, make sure you are comfortable uploading selected media to NemoVideo's cloud API, using or creating a NEMO_TOKEN, and potentially consuming rendering credits. Do not provide sensitive media unless you trust the provider.

Findings (5)

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.

What this means

Any audio, video, images, URLs, and prompts the user provides for rendering may be processed by NemoVideo's cloud service.

Why it was flagged

The skill clearly discloses that user media and related workflow data are sent to an external cloud backend for processing.

Skill content
All calls go to `https://mega-api-prod.nemovideo.ai` ... **Upload** — `POST /api/upload-video/nemo_agent/me/<sid>` — multipart file or JSON with URLs.
Recommendation

Only upload media you are comfortable sending to that provider, and avoid private or rights-sensitive files unless you trust the service.

What this means

The token can authorize requests to the rendering backend and may be tied to credits or a session.

Why it was flagged

The skill uses a bearer token, or creates an anonymous token, to authorize cloud rendering and credit-related operations.

Skill content
Look for `NEMO_TOKEN` in the environment ... POST `https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token` ... All requests must include: `Authorization: Bearer <NEMO_TOKEN>`.
Recommendation

Keep NEMO_TOKEN private, use a dedicated token if possible, and monitor credit usage.

What this means

Backend responses may cause the agent to continue editing, querying state, or exporting within the user's session.

Why it was flagged

The skill instructs the agent to treat backend GUI-style responses as operational instructions, which is expected for this service but gives the remote backend influence over subsequent API actions.

Skill content
Backend says | You do ... "click [button]" / "点击" | Execute via API ... "Export button" / "导出" | Execute export workflow.
Recommendation

Confirm before any export or credit-consuming action if the user has not clearly requested it.

What this means

Users have limited registry-level information for independently verifying the service behind the skill.

Why it was flagged

There is no local code or install script, but the provider/provenance information is sparse for a skill that relies on an external API.

Skill content
Source: unknown; Homepage: none; No install spec — this is an instruction-only skill.
Recommendation

Review the provider and terms outside the skill before sending sensitive media.

What this means

A render may continue server-side even if the local session is interrupted.

Why it was flagged

Cloud render jobs can persist outside the immediate local interaction, though this is disclosed and aligned with rendering.

Skill content
The session token carries render job IDs, so closing the tab before completion orphans the job.
Recommendation

Avoid starting renders unintentionally, and check job/status or credits after interrupted sessions.