exa-search-hardened

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly calls the Exa Search API (see scripts/exa_search.mjs POST to https://api.exa.ai/search) and SKILL.md documents returning titles/URLs/snippets and an optional --text flag to include full page text from public websites, so untrusted third‑party web content is ingested and can directly influence agent behavior.