captions

PassAudited by ClawScan on May 1, 2026.

Overview

This is a coherent YouTube captions skill that calls TranscriptAPI, but it requires a TranscriptAPI API key and may help create and store one persistently.

Before installing, be comfortable with YouTube links being sent to TranscriptAPI and with the agent storing a TranscriptAPI API key for later use. Prefer a trusted secret store, confirm account creation before providing an email or OTP, and revoke the key if you stop using the skill.

Findings (2)

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

When the skill is used, the requested YouTube video identifier is sent to TranscriptAPI and one API credit may be consumed.

Why it was flagged

The skill directs the agent to make an authenticated external API request to TranscriptAPI using the requested YouTube URL or ID. This is purpose-aligned for caption retrieval, but it is still an external data flow.

Skill content
GET /api/v2/youtube/transcript ... `video_url` ... `Authorization: Bearer $TRANSCRIPT_API_KEY`
Recommendation

Use it for videos you are comfortable sending to TranscriptAPI, and monitor usage if credits matter.

What this means

The agent may store a TranscriptAPI key so future sessions can call the service without asking again.

Why it was flagged

The setup flow handles a service API key and instructs the agent to persist it. This credential use is disclosed and necessary for the integration, but it gives the agent ongoing delegated access to the TranscriptAPI account.

Skill content
You now have a string that starts with `sk_`. This is the `TRANSCRIPT_API_KEY`. Store it persistently using whatever method is correct for this environment
Recommendation

Store the key in a proper secret manager or trusted agent environment setting, avoid putting it in broadly readable files, and revoke it from the provider dashboard if no longer needed.