spec-driven

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow explicitly runs web research and dispatches research sub-agents (see SKILL.md "Knowledge Verification Chain" Step 4: "Web search" and references/design.md Step 5 which dispatches research subagents to create .artifacts/research/{topic}.md), meaning it fetches and ingests open/public third-party sources to inform design decisions that materially affect subsequent actions.