multi-search-engine

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md and references/international-search.md explicitly instruct the agent to perform web_fetch calls against public search engines (e.g., Google, DuckDuckGo, Brave, WolframAlpha) and to read/analyze those results, which are untrusted third‑party/user‑generated web content that can influence subsequent tool use and decisions.