Research.
Notes from the lab, and the public record of what our engine has broken. All of it verifiable.
Notes from the lab
All notes →- Jul 15, 2026
AI Agents Are Entering the Kernel
The real benchmark for AI security research is whether a finding survives maintainer review, lands upstream, and gets carried into the software people actually run. The public record is starting to show ours does.
- Jul 14, 2026
Your validator checked one value. Your app used another.
A validation soundness bug class in JavaScript. Some widely-used validators inspect the caller's live object and hand it back unchanged, so a getter or Proxy can slip a value past the schema that the app then uses. We confirmed it in class-validator and superstruct. joi and zod are safe, and the reason they are safe is the fix. Reported upstream.
- Jul 11, 2026
One Research Loop, Evidence Matched to the Target
Why vulnerability research needs target-specific harnesses and oracles, but one shared discipline for evidence, novelty, and impact.
- Jul 9, 2026
A 15-Year-Old Out-of-Bounds Read in the Linux Kernel's NFC Stack
An unauthenticated NFC peer could crash the kernel with one malformed frame. The bug shipped in 2011 and sat in every kernel since. Automated source analysis surfaced it. The fix is accepted upstream in the NFC maintainer tree and heading to mainline (ed85d4cbbfaa).
- Jun 21, 2026
Fixing the Linux Kernel: Upstream Memory-Safety Contributions
The same automated research pipeline that audits npm packages now reads kernel C and has landed 0sec-authored fixes in the mainline Linux kernel, each maintainer-reviewed and flowing into stable where applicable. Here's what merged, and how.
- Jun 3, 2026
Switzerland Has No Doorbell
Nine in ten Swiss websites publish no security.txt, so a researcher has no way to report a vulnerability. We checked every .ch domain in two public lists. Here is the data, and the ten-minute fix.
- May 16, 2026
Agentic Pentesting: The Shell-First Architecture
Shell-first design as a discovered architecture for autonomous pentesting agents. One bash tool outperforms a structured toolkit across public benchmarks, the AI/LLM security suite, and adjacent domains.
- May 16, 2026
The Triage Moat and Multi-Benchmark Validation
Ablation testing as scientific method: an 11-layer false-positive triage stack, the one broken layer that almost masked the rest, and the multi-benchmark portfolio that surfaces what a single suite would miss.
- May 16, 2026
Web Vulnerability Benchmarks: Methodology and Environment Verification
Over 37% of standard web vulnerability challenges fail to build on clean systems because Docker images and package repos rot. Read the benchmark score without knowing the substrate and you cannot compare it to anything.
- May 7, 2026
Orchestration, Not Frontier: What the IronCurtain Post Means for 0sec
Niels Provos shipped a vulnerability-discovery framework that replicates Mythos-class findings on commercial models, plus one autonomous CVE on an open-weight model. It is the same bet 0sec is built on. Here is what we already do, what we need to borrow, and the four gaps we are closing.
- Apr 7, 2026
Deleting better-sqlite3, and What It Cost
An engineering note from building 0sec's engine. We migrated the persistence layer from better-sqlite3 to a pure-WASM SQLite build. What broke, what we kept, and why dropping the native module made the engine run identically on every Node.js version.
- Apr 6, 2026
Introducing 0cloud
An autonomous AI attacker on contract, pointed at your product. Closed beta, by application only. Founder-led from Zürich.
- Apr 4, 2026
The Attack Surface Traditional Benchmarks Don't Test
Traditional web vulnerability benchmarks miss the entire AI/LLM security attack surface. Prompt injection, jailbreaks, MCP tool abuse: none of it appears in standard 104-challenge web security suites.
- Mar 29, 2026
Blind Verification: How False Positives Get Killed
Every security scanner drowns its users in false positives. Closing that gap took three architectural attempts before one of them worked.
- Mar 26, 2026
How AI Agents Found Vulnerabilities in Popular npm Packages
A three-week methodology validation. Claude Opus, applied systematically to popular npm packages, surfaced 73 findings and disclosed vulnerabilities across packages with 55M+ weekly downloads. Here is how the workflow operates.
- Mar 26, 2026
The Age of Agentic Security
If AI agents can write 1,000 pull requests a week, AI agents should be testing 1,000 pull requests a week. The asymmetry is about to collapse.
The public track record.
Every vulnerability we've disclosed. Each one links to its public record.
Reviewed by engineers at
GHSA-8gq3-vp5j-2grp CVE-2026-63801 CVE-2026-63831 Merged upstream CVE-2026-63944 Merged upstream In review In review Merged upstream In review In review In review In review In review CVE-2026-52746 In review In review Merged upstream In review In review Merged upstream In review In review Queued upstream In review In review In review In review In review In review In review In review In review In review In review In review In review Updated continuously. Embargoed findings appear once they're fixed.
Work with the lab.
You build critical software, or you break it for a living. Let's talk.