brainstorming

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md mandates a default-on "Research phase" that explicitly dispatches a "general-purpose" subagent to gather web (trends + discourse) content (public web/discourse) and requires recording those findings into the spec, so the agent will fetch and interpret untrusted third‑party web/user‑generated content that can influence subsequent design decisions.