web-clone
Warn
Audited by Snyk on Jul 14, 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 required workflow for Mode B — reconstruct explicitly performs runtime browser reconnaissance (“browser-MCP/Computer-Use: full-page screenshots… sweep scroll/click/hover… extract global design tokens… map page topology”), which implies ingesting outsider-authored page content (the target website’s DOM/text/styles) into the agent’s LLM context via the extraction/spec-writing steps (e.g., writing
docs/research/components/<name>.spec.mdfrom computed styles and verbatim content).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata