roadmap-with-file

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly performs external web research using web.run (see Phase 3 "Research" / "Execute web.run for architecture patterns and best practices"), which fetches open/public third‑party content that the agent reads and uses to modify the roadmap and decisions, creating a clear vector for indirect prompt injection.