ad-creative

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly pulls and ingests third-party ad performance data from external ad platforms (see "How This Skill Works" core loop and "Tool Integrations" with commands like node tools/clis/google-ads.js reports get and meta-ads insights get), which are untrusted/user-generated sources whose contents are analyzed and used to drive generation and upload decisions — enabling indirect prompt-injection risk.