find-influencers

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 calls public X/social-media endpoints (POST /extractions, GET /extractions/{id}/results and GET /x/users/{username} on xquik.com) to ingest user-generated account bios and profiles, which the agent reads and uses to shortlist/influence actions, exposing it to untrusted third-party content that could carry indirect prompt injection.