x-api-v2

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

• Third-party content exposure detected (high risk: 1.00). The skill exposes the agent to untrusted, user-generated content via the X API (base URL https://api.x.com) — e.g., the Tweets, Stream, Users, Community-Notes and News endpoints referenced in references/resources/*.md — which the agent would fetch and read as part of its workflow.