An AI agent escaped Google's kvmCTF sandbox
Our AI agent spent weeks inside nested KVM, built a 14,338-line kernel exploit harness, and made Google’s live host hand back the flag. On June 17, 2026, pwn was four attempts into an official Google kvmCTF slot. The exploit ha launched a nested VM, rewritten its own EPT through an emulated VMX instruction, rotated eight EPT roots, allocated 49,152 sparse mappings, groomed 8,192 pages, switched views with VMFUNC, and walked 1,002 aliases back to the same page.
- ▪Our AI agent spent weeks inside nested KVM, built a 14,338-line kernel exploit harness, and made Google’s live host hand back the flag.
- ▪On June 17, 2026, pwn was four attempts into an official Google kvmCTF slot.
- ▪The exploit ha launched a nested VM, rewritten its own EPT through an emulated VMX instruction, rotated eight EPT roots, allocated 49,152 sparse mappings, groomed 8,192 pages, switched views with VMFUNC, and walked 1,002 aliases back to the
Hacker News (AI / LLM) files mainly under ai. We currently carry 6,836 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | PWN.AI |
| Canonical URL | https://pwn.ai/blog/kvmescape |
| Publication time | Tue, 29 Sep 2026 11:09:29 +0000 |
| Retrieval time | 2026-09-29T11:15:11.518Z |
| Last seen | 2026-09-29T11:15:11.518Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | cmZTAru77kNE · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Our AI agent spent weeks inside nested KVM, built a 14,338-line kernel exploit harness, and made Google’s live host hand back the flag. On June 17, 2026, pwn was four attempts into an official Google kvmCTF slot. The exploit ha launched a nested VM, rewritten its own EPT through an emulated VMX instruction, rotated eight EPT roots, allocated 49,152 sparse mappings, groomed 8,192 pages, switched views with VMFUNC, and walked 1,002 aliases back to the same page. The first three attempts returned zero.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at PWN.AI.
Discussion
0 commentsMore from PWN.AI
