load-context

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

• Third-party content exposure detected (high risk: 0.70). The skill optionally queries community-contributed "Global Best Practices" via mcp__mem0__search_memories (user_id "orchestkit-global-best-practices") — anonymous, opt-in user-generated content that the agent will read and incorporate into session output, creating a vector for indirect prompt injection.