x-ai-digest

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly scrapes and ingests user-generated posts from X's public "For You" feed (visiting https://x.com/home and extracting tweet content as shown in SKILL.md and references/scraping-guide.md), so the agent will read untrusted third‑party content that could contain indirect prompt injection.