find-twitter-influencers

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests public third-party pages (Exa searches with contents.text for listicles), plus Fiber and Scrape Creators results (LinkedIn profiles and Twitter tweets), and the agent is required to read and act on that untrusted user-generated content to extract handles, score candidates, and drive follow-up tool calls.