man

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly describes integration with public community sources (e.g., "AI Explanation" leveraging ManKier and "Hybrid Support" accessing TLDR content via the ":" prefix, see SKILL.md and examples like "x man :ssh"), meaning the agent will fetch and interpret untrusted, user-generated third-party content that can influence its actions.