sandbox — An isolated environment where AI-generated code or agent actions run without being able to touch anything real.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
sandboxAn isolated environment where AI-generated code or agent actions run without being able to touch anything real.Full definition → filesystem and network access is the missing piece for running Claude Code in longer autonomous sessions without rubber-stamping permission prompts — it moves the trust boundary from per-action approval to an enforced isolation layer.
Key quotes
“In our internal usage, we've found that sandboxing safely reduces permission prompts by 84%.”
“Sandboxing ensures that even a successful prompt injection is fully isolated, and cannot impact overall user security.”
“This way, a compromised Claude Code can't steal your SSH keys, or phone home to an attacker's server.”
“Without network isolation, a compromised agent could exfiltrate sensitive files like SSH keys; without filesystem isolation, a compromised agent could easily escape the sandbox and gain network access.”
