Crawl From X
ReviewAudited by ClawScan on May 1, 2026.
Overview
This appears to be a disclosed X/Twitter scraping skill, with the main user-facing risks being its use of a logged-in browser session and local storage of crawled posts/media.
Before installing, confirm you trust the source, understand that the crawler will use your logged-in X/Twitter browser session, and decide where/how long you want scraped posts and downloaded media retained. For lower risk, use a separate browser profile or X account and avoid cron scheduling unless you truly want unattended daily crawling.
Findings (4)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The skill can browse X/Twitter content available to the logged-in account when you run the crawler.
The skill uses the user's logged-in X/Twitter browser session to access content, which is expected for this scraper but is still delegated account/session access.
在安装了 Browser Relay 扩展的浏览器中登录 X（Twitter） - 技能会使用已登录的会话抓取内容
Use a dedicated browser profile or X account if possible, and only run the crawler when you are comfortable with it using that logged-in session.
Users have less provenance information for deciding whether to trust the included scripts.
The package includes local Python scripts to run, but the registry metadata does not provide a verified source or homepage.
Source: unknown; Homepage: none
Review the installed files and prefer installing from a trusted, matching upstream source before running the Python commands.
Crawled posts and media remain on disk and may later be read or summarized by an agent; that content should be treated as untrusted web/social content.
The skill stores retrieved social-media content and downloaded media locally as persistent Markdown and image/video files.
posts_YYYYMMDD_HHMMSS.md - 完整内容（Markdown）... images/ - 下载的图片和视频
Keep the results directory private, delete old outputs when no longer needed, and do not treat crawled post text as instructions.
If you add the cron job, the crawler will keep running on a schedule and continue using the configured browser/session environment.
The README documents an optional cron setup for unattended recurring crawls; it is user-directed, not hidden.
添加到 crontab，每天早上 8 点运行 ... python3 skills/crawl-from-x/scripts/craw_hot.py crawl
Only add scheduled execution deliberately, and remove the cron entry if you no longer want automatic crawls.