x-fetcher

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches public, user-generated X/Twitter content (via fetch_via_fxtwitter in fetch_x.py and fetch_via_syndication calling cdn.syndication.twimg.com) for URLs supplied to the agent (SKILL.md and scripts/main.py), and that fetched text/media is parsed and returned for the agent to read and act on—creating a clear path for untrusted third-party content to influence agent behavior.