Crawl4ai

AI-powered web scraping framework for extracting structured data from websites. Use when Codex needs to crawl, scrape, or extract data from web pages using AI-powered parsing, handle dynamic content, or work with complex HTML structures.

Install only if you need browser-based web scraping. Use it only on sites and pages you are authorized to access, avoid the Cloudflare/proxy bypass guidance, do not run gh auth login for this skill unless a separate GitHub task requires it, and treat screenshots, saved HTML, and extracted data as potentially sensitive.

Type: OpenClaw Skill Name: crawl4ai Version: 1.0.0 The OpenClaw AgentSkills skill bundle 'crawl4ai' is classified as suspicious. While its primary purpose is benign web scraping, it provides powerful capabilities that, if misused by a malicious prompt to the AI agent, could lead to harmful actions. Specifically, the `AsyncWebCrawler` allows arbitrary network requests to any URL and the `js_code` parameter enables the execution of arbitrary JavaScript within the browser context of the scraped page (as seen in `SKILL.md`, `references/api_reference.md`, and `references/examples.md`). Although there is no explicit malicious intent or instructions for the agent to perform harmful actions within the skill's own files, these broad capabilities present a significant attack surface for prompt injection or other forms of misuse against the agent, allowing it to potentially access sensitive data or perform unauthorized actions on external websites.