Skills youtube-batch-transcript-extractor-api-skill
📦
youtube-batch-transcript-extractor-api-skill
Content revision r2 Safe 🌐 Network access🔑 Env variables⚙️ External commands
Extract YouTube Transcripts in Batches
Collecting transcripts from multiple YouTube videos takes time and custom scraping. This skill uses BrowserAct to return transcripts and related metadata from keyword searches.
Supports: Claude Codex Code(CC)
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-batch-transcript-extractor-api-skill" from https://skillstore.io/skills/browser-act-youtube-batch-transcript-extractor-api-skill.md and its manifest at https://skillstore.io/api/skills/browser-act-youtube-batch-transcript-extractor-api-skill/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.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.
Test it
Using "youtube-batch-transcript-extractor-api-skill". Extract two videos about workflow automation uploaded this week.
Expected outcome:
- Video title: Example workflow automation briefing
- Video URL: [YouTube video URL]
- Publisher: Example channel
- Channel link: [YouTube channel URL]
- Video likes count: Available count
- Subtitles: Complete transcript returned by BrowserAct
Using "youtube-batch-transcript-extractor-api-skill". Extract recent videos when BROWSERACT_API_KEY is not configured.
Expected outcome:
The task stops and reports that the BrowserAct API key is missing before any API request is made.
Security Audit
Safev7 • 7/23/2026 Open versioned report
The skill intentionally sends search parameters, task identifiers, and a bearer credential to the BrowserAct API over HTTPS. Most alerts are safe API use or Markdown formatting, but the instructions improperly ask users to provide an API key directly to the agent.
2
Files scanned
192
Lines analyzed
6
Review items
0
False positives ignored
Capability review items (6)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
High
Generic API/secret keys
print("3. Provide it to me or set it as an environment variable (BROWSERACT_API_KEY).", flush=True)
The error message tells the user to provide the API key to the agent. Soliciting a secret through conversation can expose it in chat history.
High
Generic API/secret keys
Before running, you must check the `BROWSERACT_API_KEY` environment variable. If it is not set, do n
The skill directs the agent to request and wait for the user's API key. This encourages secret disclosure through an AI conversation.
Medium
Ruby/shell backtick execution
```bash
The fenced Bash section instructs the agent to run the bundled Python script. This intentional process execution activates the script's network behavior.
Low
Python HTTP libraries
res = requests.post(f"{API_BASE_URL}/run-task-by-template", json=payload, headers=headers, timeout=3
The POST intentionally sends search parameters and a bearer credential to BrowserAct. This is expected behavior, but it exposes user data to an external service.
Low
Python HTTP libraries
status_res = requests.get(f"{API_BASE_URL}/get-task-status?task_id={task_id}", headers=headers, time
The polling request sends the task identifier and bearer credential to BrowserAct. The destination is fixed, but this remains intentional external communication.
Low
Python HTTP libraries
task_info = requests.get(f"{API_BASE_URL}/get-task?task_id={task_id}", headers=headers, timeout=30).
The result request sends the task identifier and bearer credential to BrowserAct. This is necessary for the feature and creates a documented network dependency.
Risk Factors
🌐 Network access (6)
🔑 Env variables (10)
scripts/youtube_batch_transcript_extractor_api.py:94 scripts/youtube_batch_transcript_extractor_api.py:94 scripts/youtube_batch_transcript_extractor_api.py:17 scripts/youtube_batch_transcript_extractor_api.py:21 scripts/youtube_batch_transcript_extractor_api.py:94 scripts/youtube_batch_transcript_extractor_api.py:100 scripts/youtube_batch_transcript_extractor_api.py:105 scripts/youtube_batch_transcript_extractor_api.py:112 SKILL.md:4 SKILL.md:20
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.
Copy report link
https://skillstore.io/skills/browser-act-youtube-batch-transcript-extractor-api-skill/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/browser-act-youtube-batch-transcript-extractor-api-skill?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/browser-act-youtube-batch-transcript-extractor-api-skill?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/browser-act-youtube-batch-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-batch-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-batch-transcript-extractor-api-skill security audit report (audit version 7) [Author version unspecified]. Skillstore. https://skillstore.io/skills/browser-act-youtube-batch-transcript-extractor-api-skill/audits/7BibTeX citation
@techreport{browser-act-browser-act-youtube-batch-transcript-extractor-api-skill-2026,
author = {browser-act},
title = {youtube-batch-transcript-extractor-api-skill security audit report (audit version 7)},
institution = {Skillstore},
year = {2026},
number = {7},
url = {https://skillstore.io/skills/browser-act-youtube-batch-transcript-extractor-api-skill/audits/7},
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-batch-transcript-extractor-api-skill security audit report (audit version 7)"
version: "unspecified"
type: report
authors:
- name: "browser-act"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/browser-act-youtube-batch-transcript-extractor-api-skill/audits/7"
identifiers:
- type: other
value: "skillstore:browser-act-youtube-batch-transcript-extractor-api-skill:audit:7"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: High 45
Architecture
85
Maintainability
87
Content
69
Community
83
Spec Compliance
What You Can Build
Build a Research Corpus
Collect recent transcripts and source metadata for qualitative coding, literature monitoring, or topic analysis.
Monitor Industry Videos
Track new videos about a market, competitor, or product and review their complete spoken content.
Prepare Analysis Datasets
Gather transcripts with titles, channels, URLs, and likes for downstream classification or summarization.
Try These Prompts
Extract a Small Batch
Extract transcripts for five YouTube videos about [topic] uploaded this week.
Apply Search Filters
Find [count] videos about [topic] uploaded [Today, This week, This month, or This year]. Return titles, URLs, publishers, likes, and subtitles.
Create an Attributed Dataset
Build a transcript dataset for [topic] from [count] videos uploaded this month. Preserve source URLs and channel details for attribution.
Collect and Compare Sources
Collect [count] recent videos about [topic], then compare recurring themes, claims, and audience signals. Cite each conclusion to its video URL and transcript.
Best Practices
- Set BROWSERACT_API_KEY in the local environment and never share it through a prompt or conversation.
- Start with one to five videos to confirm search quality before requesting a larger batch.
- Respect YouTube terms, transcript rights, privacy requirements, and source attribution when storing or analyzing results.
Avoid
- Do not paste an API key into chat, command arguments, source files, or logs.
- Do not use unsupported upload-date values or a nonnumeric video limit.
- Do not assume every video provides complete subtitles, likes, or unrestricted regional access.
Frequently Asked Questions
What credentials are required?
A BrowserAct API key is required. Configure it locally as BROWSERACT_API_KEY before running the script.
Which search controls are supported?
Provide one keyword string, a supported upload-date filter, and a numeric video limit.
How long can extraction take?
The script polls every ten seconds for up to ten minutes. Browser automation may take several minutes.
What information can each result include?
Results can include a title, video URL, publisher, channel link, likes count, and complete subtitles.
Can I provide a list of video URLs?
No. The included script starts a BrowserAct template from a keyword search and does not accept a URL list.
What happens when a task fails?
Guidance allows one rerun for nonauthorization failures. Invalid authorization errors require the user to replace or reconfigure the key.
Developer Details
Author
browser-actLicense
MIT
Skillstore revision
r2
Version notice
The author did not declare a version.
Ref
a39a91716eadede5f4cdefd78178fed4e837a128
Maintenance freshness
7/24/2026
Usage
3 downloads · 152 views
File structure