extract-site
Warn
Audited by Snyk on Jun 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). The required runtime workflow “Website Extraction” takes a user-supplied public URL and then gathers visual/CSS data from that outsider website (public web content fetched/scraped and browser-extracted text/styles), which is then ingested into the agent’s LLM context to generate DESIGN.md/tokens.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata