x-webmcp

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs using x-webmcp-cli to fetch user-generated content from X (e.g., timeline.home.list, search.tweets.list, tweet.get, tweet.conversation.get on https://x.com) and to feed threads to grok.chat, so the agent ingests untrusted third‑party social-media content that could influence subsequent actions.