tweet-series-extractor

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly navigates to and scrapes public X/Twitter pages (e.g., https://x.com/username and https://x.com/username/status/ID) using get_page_text, read_page, and injected javascript to extract tweet content, links, and engagement metrics—i.e., untrusted, user-generated third-party content is read and used to drive the agent's extraction and follow-up actions.