ad-creative-builder

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

• Third-party content exposure detected (medium risk: 0.30). The workflow ingests free text at runtime from outsider-controlled sources via “Read the destination” (extracting headline/value prop/CTA from the user-supplied destination URL and treating exported CSV/scraped landing-page copy/pasted competitor ads as untrusted input), so an outsider can submit poison text by providing a destination page/contents the agent reads.