twitter-automation

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

• Third-party content exposure detected (high risk: 0.90). This skill exposes the agent to untrusted, user-generated content via the X integration—e.g., the Available Apps and examples include x/post-get (Get Tweet Details) and x/user-get (Get User Profile) which fetch public tweets/profiles that the agent could read and then use to decide actions like posting, retweeting, DMs, or follows.