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.md explicitly instructs the agent to fetch and ingest untrusted public web content—e.g., Exa search listicle pages via contents.text, Fiber profile search results, and Scrape Creators/LinkedIn pages—and to parse that text to extract handles and bios which directly drive filtering, scoring, and follow-up tool calls, so third‑party content can materially influence agent actions.