Free Video Subtitle

PassAudited by ClawScan on May 11, 2026.

Overview

This skill appears to be a cloud video-captioning integration that uses a NemoVideo token and uploads user-selected videos to a stated backend, with no artifact-backed signs of deception or destructive behavior.

Before installing, confirm you are comfortable using the NemoVideo backend, sending selected videos to that service, and allowing the skill to create or use a NEMO_TOKEN-backed session. The provided artifacts do not show hidden code, local destructive actions, or unrelated credential use.

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.

What this means

Opening the skill may create a backend session before a video is processed.

Why it was flagged

The skill directs the agent to make automatic backend API calls on first use. This is coherent with a cloud-processing workflow, but it is still an automatic external action users should notice.

Skill content
When a user first opens this skill, connect to the processing backend automatically. Briefly let them know (e.g. "Setting up...").
Recommendation

Only use the skill if you are comfortable with it contacting the stated NemoVideo backend when invoked.

What this means

The token can authorize cloud video-processing actions and may be tied to credits or a session.

Why it was flagged

The skill uses a bearer token to authenticate all backend requests. This is expected for the service, and the artifact does not show hardcoded tokens or unrelated credential use.

Skill content
Include `Authorization: Bearer <NEMO_TOKEN>` and all attribution headers on every request
Recommendation

Use a dedicated token for this service and do not share NEMO_TOKEN outside the intended backend.

What this means

Videos, URLs, and related prompts may be processed by the external NemoVideo service.

Why it was flagged

The skill sends user-selected video files or URLs to an external provider for processing. This is central to the skill’s purpose, but it affects user media privacy.

Skill content
**Upload**: POST `/api/upload-video/nemo_agent/me/<sid>` — file: multipart `-F "files=@/path"`, or URL: `{"urls":["<url>"],"source_type":"url"}`
Recommendation

Upload only media you are comfortable sending to that provider, especially if it contains private people, audio, locations, or business content.

What this means

Backend responses may cause the agent to continue workflow steps such as querying state or exporting within the same service.

Why it was flagged

The skill tells the agent to treat backend messages as workflow instructions. This appears intended for the provider integration, but it means remote responses can influence subsequent API actions.

Skill content
The backend assumes a GUI exists. Translate these into API actions: "click [button]" / "点击" | Execute via API
Recommendation

For important edits or exports, ask the agent to summarize the planned action before proceeding.