grapesjs

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

• Third-party content exposure detected (high risk: 0.90). The skill's docs and init/config reference explicitly allow loading arbitrary external content — e.g., editor.canvas.scripts/styles in SKILL.md, AssetManager assets and uploads (references/api-reference.md and assets section), dynamic script loading in references/components-js-reference.md, and remote storage urlLoad/urlStore in references/storage-reference.md — so the agent will ingest and render/run untrusted third-party resources that can change behavior.