design-structure

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

• Third-party content exposure detected (high risk: 0.70). The skill's core workflow explicitly requires performing "a lightweight feasibility check (web search or doc lookup)" when flagging external dependencies (see SKILL.md Core Responsibilities #8), which directs the agent to fetch and interpret open/web-sourced documentation whose untrusted content could influence decisions and tool use.