Simon Willison highlights a 404 Media report about hackers taking over Instagram accounts through Meta's AI support bot. A video reportedly shows an attacker asking the bot to link a target account to a new email address and providing a code. Willison argues this barely qualifies as prompt injection: the core failure was granting a support bot enough authority to fast-forward the account recovery process.
Vercel announced a team-wide provider allowlist for AI Gateway. Based only on the title, the update appears focused on centralized governance over which AI providers a team may use. This is likely most relevant to teams managing compliance, cost control, and approved provider access across multiple projects, rather than a new model capability.
本文介紹安全存取控制平台 Indent 的實踐案例。Indent 透過 Next.js 和 Vercel 構建其核心平台,利用 Edge Middleware 實現低延遲的身份驗證,並透過 Serverless Functions 處理複雜的權限審批工作流。Vercel 的合規性與預覽部署功能,幫助 Indent 在維持高安全標準的同時,大幅提升開發團隊的迭代效率。