personalization-at-scale-skill

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow explicitly instructs the agent to research prospects using public third-party sources such as LinkedIn activity, company news, blog posts, and press/funding announcements (see "Research Sources" and "Usage Instructions" steps), meaning the agent must fetch and interpret untrusted user-generated/public web content to drive personalization decisions.