clone-website

Warn

Audited by Snyk on Apr 9, 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 workflow explicitly instructs the agent to open and scrape arbitrary target URLs using agent-browser (e.g., "agent-browser open [TARGET_URL]", document.documentElement.outerHTML, asset-discovery and getComputedStyle eval scripts in Phase 1), so the agent ingests untrusted third-party web content and uses that data to drive extraction, build decisions, and dispatched builder actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 9, 2026, 11:56 AM
Issues
1