social-content

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly requires web research ("If web browsing is available, verify current platform patterns and cite sources") and the skill targets public social platforms (LinkedIn, X, Instagram, TikTok), so the agent will fetch and interpret untrusted public/user-generated web content that can materially influence content and actions.