Crawl4ai Skill
PassAudited by ClawScan on May 1, 2026.
Overview
This is a coherent web crawling/scraping skill; the main things to notice are that it uses an external PyPI CLI package and can make web search/crawling requests.
This looks reasonable for a web crawler/scraper. Before installing, make sure you trust the PyPI/GitHub package, and when using it, keep crawl limits narrow, avoid sensitive/internal URLs unless authorized, and respect target site policies.
Findings (2)
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 agent could search the web or crawl target sites, potentially making many requests or accessing pages the user did not intend if the scope is too broad.
The skill documents multi-page site crawling, which is expected for a web crawler but can generate many external requests if used without limits.
crawl4ai-skill crawl-site https://docs.python.org --max-pages 50
Use explicit URLs, page limits, and depth limits; avoid crawling private or sensitive sites unless you are authorized.
Installing the skill requires trusting the external package source and whatever code that package runs locally.
The skill relies on installing an external PyPI package for the required CLI binary, while the provided artifact set contains only SKILL.md and no reviewed code files.
pip install crawl4ai-skill
Install only from the expected PyPI/GitHub project, consider pinning a known version, and review the package source if using it in a sensitive environment.