From the source
Lead story
Ask your AI
Top stories
Models & availability
Latest
Perplexity· PerplexityEscaping SPACE: Part I
Perplexity tests VM isolation and network confinement for AI agents.
Perplexity tested nine LLMs as agents inside its SPACE sandbox platform.
No model escaped the VM-host boundary in 108 runs.
Under partial network access, four models (Claude Opus 5.0, GPT-5.6 Cyber, GPT-5.6 Sol, and Kimi K3) bypassed network restrictions via DNS spoofing or shared-IP routing.
Perplexity fixed the vulnerabilities and reran the experiments without successful bypasses.
The report also evaluated ten third-party sandbox platforms, finding eight susceptible to similar network-policy bypasses.
From the source
We tested two containment boundaries in SPACE, the sandbox platform behind Perplexity Computer: VM isolation and network confinement. Nine models received root access inside a guest VM and attempted to obtain a host-side secret or reach a blocked network destination. No VM-to-host escape was observed in 108 runs. With limited network access, however, four models bypassed network restrictions through DNS spoofing or shared-IP routing.