brand-setup

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly asks for and stores user-provided public URLs or text snippets as "Sample content" (Step 4: "Share 2-3 URLs or text snippets") and competitor URLs (Step 6) and mandates using those voice samples to set the brand voice that will materially influence generated outputs, so untrusted third‑party content is ingested and can change agent behavior.