Bilibili & YouTube Watcher
v1.0.0Fetch and read transcripts from YouTube and Bilibili videos. Use when you need to summarize a video, answer questions about its content, or extract informati...
⭐ 9· 3.6k·44 current·45 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the included script and README. The only required binary is yt-dlp, which is exactly what a transcript fetcher needs. No extraneous credentials, config paths, or unrelated binaries are requested.
Instruction Scope
SKILL.md and README instruct the agent to run scripts/get_transcript.py which invokes yt-dlp in a temporary directory and prints cleaned transcript text. The instructions do not request or read unrelated files or env vars. Note: README suggests using cookies or proxies to mitigate Bilibili rate limits, but the script itself does not accept cookie inputs — this is an informational suggestion, not hidden data collection. The script adds User-Agent/Referer headers for Bilibili, which is plausible for bypassing anti-scraping but should be noted as network-affecting behavior.
Install Mechanism
Install spec in the registry lists a brew formula for yt-dlp (a standard, well-known source). SKILL.md metadata also mentions a pip install option — a minor inconsistency between the declared install specs but both are common, legitimate ways to obtain yt-dlp. No downloads from untrusted or shortened URLs are present.
Credentials
The skill requests no environment variables or credentials. The script runs yt-dlp which will access the network (expected). There are no secret-like env vars declared or accessed in the code.
Persistence & Privilege
always is false and the skill does not request persistent or elevated agent privileges. It writes only to a temporary directory while extracting subtitles and prints results to stdout; it does not modify other skills or system-wide configuration.
Assessment
This skill appears to do exactly what it says: run yt-dlp to download subtitles, clean them, and print a transcript. Before installing: (1) be aware yt-dlp will make network requests to third-party sites (YouTube/Bilibili) and may download subtitle files, (2) yt-dlp is a separate tool — install it from a trusted source (brew or pip) and keep it updated, (3) the README mentions using cookies/proxies for Bilibili rate limits but the script does not send browser cookies automatically — if you plan to use cookies you must supply them manually via yt-dlp options, and (4) if you allow agents to invoke skills autonomously, note this skill accesses the network but does not access secrets or persistent storage. The only minor inconsistency is that SKILL.md metadata lists a pip install option while the registry install spec lists brew; both are normal ways to obtain yt-dlp but you may want to confirm the installation method you prefer.Like a lobster shell, security has layers — review code before you run it.
latestvk97d38sr36p9b0spqybbqrxsvn81d5m3
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
📺 Clawdis
Binsyt-dlp
Install
Install yt-dlp (brew)
Bins: yt-dlp
brew install yt-dlp