aisa-tavily

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

• Third-party content exposure detected (high risk: 1.00). The skill invokes AIsa's Tavily web-search and extraction endpoints (scripts/search.mjs posts to https://api.aisa.one/apis/v1/tavily/search and scripts/extract.mjs posts to https://api.aisa.one/apis/v1/tavily/extract) to retrieve content and raw page text from arbitrary public URLs and web search results, which are untrusted/open-web user-generated third-party content that the agent consumes and displays.