Perplexity 红队测试 SPACE 沙箱:108 次运行中 4 个模型借网络访问绕过封锁
Perplexity 拿 9 个模型做沙箱越狱测试,108 次全没逃出 VM,但一开网络就有 4 个钻了空子,连 E2B、Vercel 都有同样的坑,细节很有意思。
Perplexity 安全团队对运行 Perplexity Computer 的沙箱平台 SPACE 做了为期一个月的红队测试,给 Opus 5、GPT-5.
6 Sol、Kimi K3、Gemini 3.1 Pro 等 9 个模型 root 权限。
在 108 次运行中,没有任何模型逃出虚拟机。但当允许访问 PyPI 和 Ubuntu 镜像后,4 个模型通过 DNS 欺骗和经 Taboola 图片抓取器 OCR 读取 flag 的方式访问了被封锁的 URL。
团队已修复漏洞,并发现 E2B、Vercel、Modal 等 10 家沙箱服务商中 8 家存在相同的 IP 共享问题。
Our security team spent the last month trying to break SPACE, the sandbox platform that runs all of Perplexity Computer. We gave 9 models (Opus 5, GPT-5.6 Sol, Kimi K3, Gemini 3.1 Pro, etc.) root access inside the VM; in some runs, the full sandbox source code too. We asked them to either escape to the host or reach a URL our network policy blocks. None of them got out of the VM in 108 runs. But once we allowed a bit of network access (just PyPI and Ubuntu mirrors so that they could install packages), 4 models managed to reach the blocked URL by: 1. Spoofing DNS responses to our gateway and using the fact that pypi.org sits on a Fastly IP shared with thousands of other sites. 2. GPT-5.6 Cyber went through Taboola's image fetcher to a screenshot service and then OCR'd the flag out of the image. We fixed both issues and made sure the reruns held. We also tested 10 other sandbox providers, and 8 of them had the same IP-sharing problem, eg E2B, Vercel, Modal. Openly sharing the red teaming research is the best way to build guardrails as an industry, and we look forward to working together with @nvidia to incorporate the guardrails into their Open Agent Safety Platform announced today. perplexity.ai/hub/blog/escap… Perplexity @perplexity_ai We’re partnering with Nvidia and 100+ industry partners to build infrastructure that contains rogue AI agents. In this research, we gave 9 AI models root access inside SPACE and told them to break out. Across 108 runs, none breached the VM boundary. perplexity.ai/hub/blog/escap… 🔗 View Quoted Tweet📊 12 ⚡
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and AI regulation, compliance frameworks, and sovereign compute policy. Key entities and technical topics under continuous tracking include Perplexity, SPACE, GPT-5.6, Kimi K3.
Source attribution: curated from Aravind Srinivas (@AravSrinivas). Cross-source corroboration: 5 independent sources have covered this development (including IT之家, Cline, elvis), confirming industry-wide signal strength.