google-ads-scripts

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

• Third-party content exposure detected (high risk: 0.90). The skill's "Broken URL Checker" (checkUrl function) uses UrlFetchApp.fetch to retrieve advertisers' final URLs (arbitrary public landing pages) and then interprets HTTP responses to pause ads and send alerts, so untrusted third-party content can directly influence script actions.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 1.00). The skill is a Google Ads Scripts reference specifically for programmatic control of Google Ads accounts and includes explicit methods to modify account spending: e.g., campaign.getBudget().setAmount(newBudget) in the "Budget Allocation by ROAS" example, pause()/enable()/remove() on entities, and other scripts that create negative keywords or change campaign settings. These are direct ad-spend/budget modification APIs (not generic browsing or generic HTTP). Although it recommends a DRY_RUN flag, the examples clearly show how to send changes that update budgets and control spending, which constitutes direct financial execution (managing ad spend budgets).