multi-search-engine

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 and references (e.g., references/international-search.md) explicitly direct the agent to fetch and interpret results from public search engines and sites (examples: web_fetch calls to Google, DuckDuckGo, Brave, WolframAlpha, etc.), which are open/public, user-generated/untrusted sources whose content the agent is expected to read and could materially influence subsequent decisions or tool use.