design-system

Warn

Audited by Snyk on Mar 28, 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.md explicitly instructs the agent to browse and scrape arbitrary live URLs (via Playwright CLI and "scraper MCP") and to ingest page HTML/CSS/screenshots (also via Stitch's screen.getHtml), meaning untrusted public webpage content is read and used to drive extraction and generation decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 28, 2026, 07:56 AM
Issues
1