web-scraper
Warn
Audited by Snyk on May 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md and EXAMPLES.md explicitly instruct the agent to fetch and crawl arbitrary public URLs (e.g., AsyncWebCrawler.arun(url=...), sitemap crawling and sitemap-based discovery in EXAMPLES.md), causing the agent to ingest untrusted, user-generated web content that is then parsed and used to drive further actions (discovering new URLs, extraction decisions, and follow-up crawls), which enables indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata