x-ops

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly navigates to and snapshots public X (twitter) pages (e.g., "goto https://x.com/home", "goto https://x.com/notifications", "snapshot -c" for timeline, profiles, search) to read user-generated content and then perform actions like like/reply/retweet, so untrusted third-party content is ingested and can influence tool actions.