vercel-ai-sdk

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/streaming.md include function-calling examples (e.g., the "searchWeb" and "getWeather" tools that call searchAPI/fetchWeatherAPI) which fetch public web/search results that the agent ingests and uses to drive subsequent tool calls and responses, exposing it to untrusted third-party content.