team-linkedin-profiles

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow (Step 3 and Step 6) explicitly runs Exa people searches and Hunter domain-searches and uses Fiber live-fetch to retrieve LinkedIn profiles and other public/user-generated web data, which the agent ingests and interprets to filter, verify, and decide which profiles to return—exposing it to untrusted third-party content that could carry indirect prompt-injection.