wix-headless

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests user-generated site data via MCP (Phase 1 Seeder returns merged into .wix/site.json.seeded. and used by downstream prompts), and requires inlining those Seeder returns into Image Phase 2 and Phase 4 Page subagent prompts (SKILL.md and ORCHESTRATION.md), so untrusted/third‑party content from the user's site is read and can materially influence agent actions (page generation, image generation, PATCHes).