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 user-generated tweets via the X API (e.g., "search recent", "read user timeline", and "Pull Recent Original Posts for Voice Modeling") and instructs using those public posts to build voice profiles and drive content generation/posting, which could allow untrusted third-party content to inject instructions.