Crawl4AI LLM-Ready Web Crawler and Scraper

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security risks were identified in the skill content. The instructions provide standard setup steps for a popular open-source project.
  • [EXTERNAL_DOWNLOADS]: The skill references the crawl4ai package on PyPI and the official GitHub repository unclecode/crawl4ai for installation and documentation source.
  • [PROMPT_INJECTION]: The skill facilitates web scraping, which naturally exposes agents to untrusted data from the internet. This creates an inherent attack surface for indirect prompt injection where malicious instructions embedded in crawled websites could target the agent.
  • Ingestion points: External web content crawled and converted to Markdown (SKILL.md).
  • Boundary markers: No specific delimiters or "ignore instructions" warnings are included in this documentation snippet.
  • Capability inventory: The scraper has network access and browser-based data extraction capabilities.
  • Sanitization: Relies on the underlying tool's Markdown conversion logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 04:05 PM
Security Audit — agent-trust-hub — Crawl4AI LLM-Ready Web Crawler and Scraper