x-api

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and ingests user-generated public content from X/Twitter via API endpoints (e.g., "https://api.twitter.com/2/users/2022779096049311744/mentions", timeline, and search/recent tweets) which the agent is expected to read and could influence replies, posting, or follow actions.