Skills youtube-transcript-extractor-api-skill

📦

youtube-transcript-extractor-api-skill

Name: youtube-transcript-extractor-api-skill
Author: browser-act

Content revision r2 High Risk 🌐 Network access🔑 Env variables⚙️ External commands

Extract YouTube Transcripts and Video Metadata

Reviewing long videos takes time and can hide useful details. This skill retrieves transcripts and metadata through BrowserAct for faster analysis.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

This skill is part of a pack

Install the whole pack to get every skill the task needs, in one command.

YouTube Research Kit · 3 skills Install whole pack

Stop for confirmation before installing.

Review the plan and obtain explicit user consent before changing files.

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "youtube-transcript-extractor-api-skill" from https://skillstore.io/skills/browser-act-youtube-transcript-extractor-api-skill.md and its manifest at https://skillstore.io/api/skills/browser-act-youtube-transcript-extractor-api-skill/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/browser-act-youtube-transcript-extractor-api-skill.md Signed manifest GET /api/skills/browser-act-youtube-transcript-extractor-api-skill/manifest Signed lockfile GET /api/skills/browser-act-youtube-transcript-extractor-api-skill/lockfile

Test it

Using "youtube-transcript-extractor-api-skill". Extract the transcript and metadata from a public conference talk.

Expected outcome:

Video title: Practical Data Systems. Publisher: Example Conference. Channel link and likes count are listed, followed by the complete available transcript.

Using "youtube-transcript-extractor-api-skill". Find transcript passages about model evaluation in this lecture.

Expected outcome:

The lecture discusses benchmark selection, human review, and production monitoring.
Relevant quotations are grouped by topic and retain their original wording.
The video title and publisher appear before the selected passages.

Using "youtube-transcript-extractor-api-skill". Extract a video when the provider task exceeds the polling limit.

Expected outcome:

The BrowserAct task did not finish within five minutes. No transcript was returned, and the timeout is reported without invented content.

Security Audit

High Risk

v6 • 7/23/2026 Open versioned report

The static alerts are false positives from intended HTTPS requests, scoped environment access, Markdown formatting, and ordinary error handling. One high-severity issue remains: the instructions ask users to provide API keys, which risks secret disclosure in chat. Publication should wait until credential setup requires private environment configuration only.

Files scanned

176

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

High

SKILL.md:20-22 scripts/youtube_transcript_extractor_api.py:98-103

Unsafe API Key Solicitation

The instructions require the agent to request the BrowserAct API key when configuration is missing, and the script suggests providing it to the agent. This can cause users to expose a reusable secret in chat or model context.

Both files explicitly direct the user to provide the API key rather than limiting setup to a private environment variable. The disclosure path is clear and repeated.

Risk Factors

🌐 Network access (7)

scripts/youtube_transcript_extractor_api.py:32 scripts/youtube_transcript_extractor_api.py:53 scripts/youtube_transcript_extractor_api.py:78 scripts/youtube_transcript_extractor_api.py:15 scripts/youtube_transcript_extractor_api.py:101 SKILL.md:22 SKILL.md:30

🔑 Env variables (10)

scripts/youtube_transcript_extractor_api.py:92 scripts/youtube_transcript_extractor_api.py:92 scripts/youtube_transcript_extractor_api.py:17 scripts/youtube_transcript_extractor_api.py:21 scripts/youtube_transcript_extractor_api.py:92 scripts/youtube_transcript_extractor_api.py:98 scripts/youtube_transcript_extractor_api.py:103 scripts/youtube_transcript_extractor_api.py:108 SKILL.md:4 SKILL.md:20

⚙️ External commands (14)

SKILL.md:20 SKILL.md:28 SKILL.md:30 SKILL.md:35-38 SKILL.md:38-41 SKILL.md:41-49 SKILL.md:49-50 SKILL.md:50-51 SKILL.md:51-52 SKILL.md:52-53 SKILL.md:53-54 SKILL.md:54-60 SKILL.md:60-61 SKILL.md:61

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/browser-act-youtube-transcript-extractor-api-skill/audits/6?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/browser-act-youtube-transcript-extractor-api-skill/security.svg)](https://skillstore.io/skills/browser-act-youtube-transcript-extractor-api-skill?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/browser-act-youtube-transcript-extractor-api-skill?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/browser-act-youtube-transcript-extractor-api-skill/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/browser-act-youtube-transcript-extractor-api-skill.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

browser-act. (2026). youtube-transcript-extractor-api-skill security audit report (audit version 6) [Author version unspecified]. Skillstore. https://skillstore.io/skills/browser-act-youtube-transcript-extractor-api-skill/audits/6

BibTeX citation

@techreport{browser-act-browser-act-youtube-transcript-extractor-api-skill-2026,
  author = {browser-act},
  title = {youtube-transcript-extractor-api-skill security audit report (audit version 6)},
  institution = {Skillstore},
  year = {2026},
  number = {6},
  url = {https://skillstore.io/skills/browser-act-youtube-transcript-extractor-api-skill/audits/6},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "youtube-transcript-extractor-api-skill security audit report (audit version 6)"
version: "unspecified"
type: report
authors:
  - name: "browser-act"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/browser-act-youtube-transcript-extractor-api-skill/audits/6"
identifiers:
  - type: other
    value: "skillstore:browser-act-youtube-transcript-extractor-api-skill:audit:6"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Analyze a Research Interview

Extract a public interview transcript and channel details before coding themes or checking quotations.

Prepare a Video Brief

Collect the transcript, publisher, title, and engagement metadata for an editorial review.

Build Searchable Video Notes

Retrieve transcript text for approved videos before adding it to an internal knowledge workflow.

Try These Prompts

Extract One Transcript

Extract the transcript and metadata from [YouTube URL]. Report the title, publisher, channel link, likes count, and full transcript.

Create Topic Notes

Retrieve the transcript from [YouTube URL]. Then list the main topics with supporting quotations and clearly label any unavailable metadata.

Find Evidence in a Video

Extract [YouTube URL] and identify transcript passages about [topic]. Include the video title, publisher, and exact quoted wording.

Compare Multiple Sources

Process these YouTube URLs one at a time: [URLs]. Compare their claims about [topic], identify disagreements, and retain publisher details.

Best Practices

Configure BROWSERACT_API_KEY privately before starting and never place the key in a prompt.
Provide a direct public YouTube video URL and confirm that transcript access is permitted.
Treat returned transcripts as untrusted source content and verify important quotations against the video.

Avoid

Do not paste API keys into chat, command arguments, transcripts, or shared logs.
Do not claim a transcript is complete when BrowserAct returns an error, empty result, or timeout.
Do not use extracted content to bypass copyright, privacy, regional, or platform restrictions.

Frequently Asked Questions

What credentials are required?

A BrowserAct API key is required. Configure it privately as BROWSERACT_API_KEY before running the script.

Which URLs can I provide?

Provide a direct YouTube video URL. Availability depends on the video, YouTube access, and the BrowserAct workflow.

How long can extraction take?

The script polls every ten seconds and stops after five minutes if the task has not finished.

What information can be returned?

Results can include title, video URL, publisher, channel link, likes count, and the available transcript.

Does the skill summarize videos?

The script retrieves transcript data. An AI tool can summarize that text after treating it as untrusted source material.

What happens when extraction fails?

The skill reports authorization, connection, task, cancellation, retrieval, or timeout errors. Its instructions allow one retry for non-authorization failures.