web-crawl4ai

Warn

Audited by Snyk on Mar 2, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill's core workflow explicitly fetches and processes arbitrary public web pages via AsyncWebCrawler.arun/arun_many (see SKILL.md and references/complete-sdk-reference.md examples such as arun("https://openai.com/api/pricing/") and batch crawling), then feeds the extracted untrusted, user-generated web content into markdown/LLM extraction and content-filtering steps that can materially influence downstream decisions and tool use.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 2, 2026, 11:02 AM