xitter

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

• Third-party content exposure detected (high risk: 1.00). The skill uses the x-cli to fetch and read tweets, timelines, searches, mentions and user lookups from X/Twitter (untrusted, user-generated content) as part of its required "Agent Workflow" and "Common Commands"—reads that the agent is expected to interpret and may drive follow-up actions like likes/retweets/replies.