solution-design

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

• Third-party content exposure detected (high risk: 0.90). The skill's research-agent explicitly performs WebSearch and ingests public URLs (see "Research Agent" WebSearch Directives and Case Studies sections in SKILL.md/agents/research-agent.md), meaning untrusted, user-generated web content is read and fed into downstream initiative generation and decisions, enabling indirect prompt injection risks.