Tool · curated 27 Aug 2026
GitHub - kontext-security/sandy: Secure agents in seconds by running them in a sandbox.
First reported github.com
Coverage timeline
Single-source analysis — first reported, latest, and curated coincide.
Why it matters
Sandy targets a core defensive gap in agentic AI deployments by isolating agent execution in a sandbox, giving defenders a way to contain compromised or misbehaving autonomous agents.
Sandy, published by kontext-security on GitHub, is an open-source tool (written in Rust) that aims to secure AI agents by running them inside a sandbox. The repository provides installable crates and scripts intended to isolate agent execution to contain risky or untrusted agent behavior.