marketing-psychology

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow explicitly includes a "live URL" starting mode in the Starting Context Router and the Audit Mode requires the agent to "read the asset carefully" (SKILL.md § Starting Context Router / § 1.2 Audit Mode), which indicates the agent will fetch and interpret public web pages (untrusted third-party content) as a required part of its analysis and recommendations.