design-audit
Warn
Audited by Snyk on Jun 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The workflow’s “Capture the UI” step for a live URL uses a web-fetch/browser-automation tool to ingest page content (public/outsider-authored text from that URL) into the agent’s LLM context for heuristic passes.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata