competitor-ad-intelligence

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

• Third-party content exposure detected (medium risk: 0.30). Outsider-authored free text can be ingested because the workflow explicitly fetches and analyzes landing-page content from URLs “found in ads,” treating fetched pages as untrusted input (via fetch_webpage: [landing_page_url]) and it also uses web_search to discover library/search results without requiring selection of a specific pre-vetted item first.