YouTube AnyCaption Summarizer

Turn YouTube videos into dependable markdown transcripts and polished summaries — even when caption coverage is messy. This skill works with manual closed ca...

This package appears to implement what it claims (YouTube transcripts plus an LLM-powered summary with local Whisper fallback), but review these points before installing: - Missing declared dependency: the scripts call the 'openclaw' CLI (openclaw infer/agent) to make LLM calls and to forward progress. The skill metadata does not list 'openclaw' as a required binary. Ensure your environment provides the OpenClaw CLI/gateway if you expect LLM/autosend features to work. - Undeclared environment variables: the code reads session/gateway/env names (YOUTUBE_LAUNCH_SESSION_KEY, OPENCLAW_SESSION_KEY, OPENCLAW_PARENT_SESSION_KEY, OPENCLAW_GATEWAY_PORT, and optional FORWARD_STATE env). If these are present in your environment the skill will use them to post messages into sessions and call the local gateway. Only set those env vars if you intend the skill to have that behavior. - File writes and model download: the installer and scripts will create ~/.openclaw/workspace and may download a Whisper model from huggingface.co into that directory. Confirm you approve creating that folder and downloading the model file (large binary). If you prefer a different location, pass --models-dir when running the scripts. - Network activity: yt-dlp will contact YouTube, and the script will curl the HuggingFace model URL. If you use --cookies or --cookies-from-browser for restricted videos, you will be providing potentially sensitive cookies for yt-dlp to use — only provide cookies you trust and prefer ephemeral handling. - Forwarding behavior: the batch runner can forward progress messages into an OpenClaw session using the openclaw agent and stores a forward-state file under ~/.openclaw/tmp. If you do not want messages forwarded, avoid setting the session-related env vars. Recommendations before installing: inspect the repository yourself (it’s bundled here), ensure you have the expected OpenClaw runtime if you want LLM summarization, verify the HuggingFace model URL is acceptable, and run the workflow in a controlled environment (or with --dry-run / --keep-intermediates) to observe behavior. If you are unsure about session forwarding, unset session-related env vars before running.

Type: OpenClaw Skill Name: youtube-anycaption-summarizer Version: 1.1.4 The skill provides a robust YouTube summarization workflow with local Whisper fallback and batch processing, but it includes several high-risk capabilities. Specifically, it supports extracting sensitive browser cookies via yt-dlp (`run_youtube_workflow.py`) and programmatically injecting messages into the active OpenClaw agent session using the `openclaw agent` CLI (`run_youtube_batch_end_to_end.py`). While these features are functionally aligned with the stated goals of accessing restricted videos and providing milestone updates, they represent a significant attack surface for data access and session manipulation. Additionally, the installation script in `SKILL.md` executes a remote download of a binary model from Hugging Face.