deepen-plan-beta

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

• Third-party content exposure detected (high risk: 0.70). The skill's workflow (Phase 3 "Select Targeted Research Agents" and Phase 4 "Run Targeted Research and Review") instructs launching external research agents such as compound-engineering:research:best-practices-researcher and compound-engineering:research:framework-docs-researcher and explicitly allows "external research" for recent documentation and best practices, which means the agent will fetch and interpret open/public third‑party web content that can materially influence plan decisions.