crawl4ai-skill

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The documentation instructs the user to install the crawl4ai-skill Python package via pip (pip install crawl4ai-skill). This package is managed by an external author and hosted on the Python Package Index (PyPI).
  • [COMMAND_EXECUTION]: The skill relies on executing the crawl4ai-skill command-line interface (CLI) to perform web scraping, searching, and site crawling operations.
  • [PROMPT_INJECTION]: The skill exposes the agent to indirect prompt injection risks by processing content from untrusted web sources. Ingestion points: Untrusted data enters the agent context through the output of the crawl and search commands (SKILL.md). Boundary markers: The skill does not implement delimiters or safety instructions to prevent the agent from following directives embedded in scraped content. Capability inventory: The skill uses a binary tool (crawl4ai-skill) capable of network access and file output (SKILL.md). Sanitization: No sanitization, validation, or filtering of external content is documented before it is passed to the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 07:45 PM
Security Audit — agent-trust-hub — crawl4ai-skill