Runtime security for AI agent sandboxes. Drop-in protection against prompt injection, secret exfiltration, and sandbox escape — works with [Vercel](https://vercel.com/sandbox), [E2B](https://e2b.dev/), [Daytona](https://www.daytona.io/), [Cloudflare Conta
@agentsh/[email protected] is safe to use (health: 70/100)
Get this data programmatically — free, no authentication.
curl https://depscope.dev/api/check/npm/@agentsh/secure-sandboxFirst published · 2026-03-08T18:55:30.297Z
Last updated · 2026-06-03T00:10:00.765Z