ClawHub
Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

YouTube Transcript & Summary

v1.0.0

Fetch YouTube video transcripts, subtitles, and generate summaries. Use when the user wants to extract text from a YouTube video, download subtitles (similar...

⭐ 0· 194·0 current·0 all-time
byJunhao@rqcker

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for rqcker/ytb-transcript.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "YouTube Transcript & Summary" (rqcker/ytb-transcript) from ClawHub.
Skill page: https://clawhub.ai/rqcker/ytb-transcript
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install ytb-transcript

ClawHub CLI

Package manager switcher

npx clawhub@latest install ytb-transcript
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
ℹ
Purpose & Capability
The name/description match the actions described in the SKILL.md (extract transcripts, timestamps, generate summaries). However the manifest lists no code or install steps while the SKILL.md explicitly references implementation artifacts (references/methods.md and scripts/fetch.py) that are not present — an internal inconsistency that should be explained.
!
Instruction Scope
The instructions are high-level and permit the agent to "attempt to fetch the transcript using available services" but do not specify which services, endpoints, or methods (YouTube Data API, third-party sites like downsub.com, web scraping, or local tooling). That vagueness could allow broad network actions or scraping behavior not evident from the description. The SKILL.md does not instruct reading system files or secrets, which is good, but the missing implementation details make the runtime behavior unclear.
✓
Install Mechanism
This is an instruction-only skill with no install spec and no code files, which minimizes installation risk. No downloads or archive extraction are declared.
ℹ
Credentials
No environment variables, credentials, or config paths are required — reasonable for a thin wrapper that uses only public resources. However, realistic transcript fetching often requires an API key (YouTube Data API) or access to third-party services; the absence of any declared credentials is notable and could indicate missing documentation about how the skill will access transcripts.
✓
Persistence & Privilege
The skill does not request elevated persistence (always:false) and does not claim to modify other skills or system settings. It can be invoked by the agent normally, which is expected for skills.
What to consider before installing
Before installing, ask the skill author or publisher to clarify runtime behavior and provide the missing implementation files or a concrete description of how transcripts are fetched: which APIs or third‑party services will be contacted, whether scraping is used, and whether any API keys will be required. If the skill will use external services (e.g., downsub-like sites or the YouTube API), confirm the exact endpoints and privacy/ToS implications. Because no code accompanies the SKILL.md, treat the skill as incomplete until you see the referenced scripts; avoid granting credentials or installing anything until that is resolved. If you proceed, test it first with non-sensitive/public videos and monitor outbound network requests.

Like a lobster shell, security has layers — review code before you run it.

latestvk97c815g9j532kefnd6q973w71837gkr
194downloads
0stars
1versions
Updated 22h ago
v1.0.0
MIT-0
Junhao@rqcker
latest
Download

YTB Transcript

Overview

This skill fetches transcripts and subtitles from YouTube videos and can generate intelligent summaries.

Use this skill for:

  • Extracting text content from YouTube videos
  • Downloading subtitles (downsub.com style)
  • Getting timestamped transcripts
  • Generating summaries of video content

How to Use

Provide a YouTube URL or video ID. The skill will:

  1. Extract the video ID from the URL
  2. Attempt to fetch the transcript using available services
  3. If requested, generate a summary of the content
  4. Return clean, usable output

Examples

Get transcript:

Get summary:

  • "Summarize this YouTube video: [url]"
  • "What are the key points from this lecture?"

Combined request:

  • "Get the transcript and summarize this video: [url]"

Available Functions

Transcript Fetching

  • Returns full transcript text
  • Can include timestamps when available
  • Supports multiple languages (prioritizes Chinese/English)

Summarization

  • Generates concise or detailed summaries
  • Can focus on key arguments, technical content, or main ideas
  • Adjustable summary length

Notes

  • Works best with videos that have subtitles (auto-generated or uploaded)
  • For videos without subtitles, it may fall back to metadata-based summarization
  • Long videos may take longer to process
  • Output is clean markdown/text suitable for research or note-taking

Resources

See references/methods.md for implementation details and supported services. See scripts/fetch.py for the core fetching logic.

Comments

Loading comments...