campaign-status

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly pulls live metrics and content from external marketing platforms (see "Pull live metrics from connected MCPs" step 5 listing google-ads, meta-marketing, linkedin-marketing, tiktok-ads, mailchimp) and surfaces pending approvals/creatives (step 4), which are untrusted third-party/user-generated inputs that the agent reads and uses to drive decisions and actions.