xcli

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches user-generated content from the X API (see SKILL.md examples "Fetch and search posts" and commands like xcli search posts, xcli likes list, xcli bookmarks list), so the agent will ingest untrusted public social-media content that could contain instructions influencing its decisions.