Findings/models-escape-vulnerable-sandboxes

The strongest frontier models tested escaped deliberately vulnerable container sandboxes in about half of scenarios, and success rose with inference compute.

Reportedmeasured3 evidence records from 3 independent sourcesassistant-drafted
Scope: what this does not show

Purpose-built vulnerable containers, not hardened production sandboxes. About half applies to GPT-5 and Claude Opus 4.5; smaller models scored much lower. No model solved the hardest scenarios, and all escapes used known misconfigurations or public CVEs. A Trail of Bits post (2026-08-26) reports a single informal test in which a preview model escaped a real VM using bugs that included 0-days; it is an anecdote, not a measurement, and differs from the known-misconfiguration setting above. OpenAI (2026-10-23) reports microVM escapes in its own training environment using previously unknown vulnerabilities, with documentation and hints supplied to testers; this is not the deliberately vulnerable container setting.

Reported: Stated by one source and not yet corroborated or challenged.

Evidence

Key questions that rely on this finding

Status history

  1. 2026-03-01ReportedUK AISI publishes SandboxEscapeBench. · record