architecture-research

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

• Third-party content exposure detected (high risk: 0.90). This skill's Workflow Step 2 "Find External Context" explicitly requires searching for and citing public third-party sources (official docs, blog posts, conference talks, and community/community discussions), so the agent will fetch and interpret untrusted user-generated/open-web content that can materially influence its architectural analysis and decisions.