twitter-agent

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, user-generated tweets/mentions via the X API (see "Step 1: Scan Mentions" and Recipe 2: "Fetch the last 50 mentions via the X API"), and the agent must read and act on that untrusted content to draft/reply/post, so third‑party tweet content could influence actions and enable indirect prompt injection.