arch-plan

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md workflow explicitly requires an "external research" phase and instructs the agent to "browse" external sources and "synthesize how the guidance changes this plan" (see SKILL.md / references/workflow-details.md external research and workflow sections), which means the agent will fetch and interpret open third‑party web content that can materially influence its planning decisions.