subagents-orchestration-guide

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

• Third-party content exposure detected (high risk: 0.90). The skill's ui-analyzer explicitly "read[s] the project's external-resources file" and "fetch[es] external UI sources via MCP/URL/file" (SKILL.md and references/monorepo-flow.md step 6), meaning the agent will fetch and interpret arbitrary external URLs/non-local resources and use those findings to drive UI analysis, specs, and design decisions.