read-x

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

• Third-party content exposure detected (high risk: 0.90). This skill fetches user-generated X/Twitter content via the public FxTwitter API endpoint (https://api.fxtwitter.com/{username}/status/{tweet_id}), causing the agent to read and render arbitrary third-party posts and long-form articles that could contain indirect prompt-injection instructions.