Vulnerability discovery

Google's Product Security team describes PageBreak, an internal agent mostly using Gemini models that hunts vulnerabilities in Google's first-party web applications and only reports findings confirmed by non-AI validators against running applications. Google reports over 500 XSS vulnerabilities found with near-zero false positives, while apps on its high-assurance web frameworks yielded only 2 XSS bugs as of 4 September 2026.

Google introduced Gemini 3.8 Flash Cyber, a cybersecurity-tuned model with more permissive cyber mitigations, available only to trusted defenders through a new Fairwind Program. Google says it prioritized vulnerability fixing over exploitation and reports 47.2% pass@1 on Collinear's CWE-Bench patching benchmark, over 70% on an internal 20-language discovery benchmark, and 2.6 times more correct Chrome patches than larger commercial models.

Anthropic reports that about 50 Glasswing partners used Claude Mythos Preview to find more than ten thousand high- or critical-severity vulnerabilities, and that its own scan of over 1,000 open-source projects produced 6,202 model-estimated high/critical findings. Of 1,752 assessed, mostly by six independent firms, 90.6% were true positives; Anthropic estimates 530 high/critical bugs disclosed, of which 75 were patched, and says triage and patching capacity, not discovery, is the bottleneck.

Help Net Security reported that Linus Torvalds described the Linux kernel security list as almost entirely unmanageable because of heavily duplicated AI-assisted reports, and that GitHub tightened its bug bounty submission requirements, with a GitHub engineer saying some programs elsewhere had shut down. The article also notes that curl ended bounty payments after a surge of low-quality AI reports.

The head of the NCSC's Vulnerability Management Group published ten questions for organizations considering AI-driven vulnerability discovery. The questions stress having a process to triage and fix findings, prioritizing exploitable issues, weighing data, permission, legal and jurisdiction risks of the chosen model, starting with the external attack surface, and planning for future models.

Anthropic launched Project Glasswing with AWS, Apple, Broadcom, Cisco, CrowdStrike, Google, JPMorganChase, the Linux Foundation, Microsoft, NVIDIA and Palo Alto Networks to use the unreleased Claude Mythos Preview for defensive security work, extending access to over 40 more organizations that maintain critical software. Anthropic committed up to $100M in usage credits and $4M in donations to open-source security groups, and reports Mythos Preview found thousands of high-severity vulnerabilities, including in every major operating system and browser.

Researchers led by Georgia Tech released OSS-CRS, a locally deployable framework for running and combining AIxCC cyber reasoning systems, noting that all seven open-sourced finalist systems depended on competition cloud infrastructure that no longer exists. Porting the winning Atlantis system, they found 10 previously unknown bugs (three high severity) in 8 OSS-Fuzz projects; OpenSSF welcomed OSS-CRS into its AI/ML Security Working Group in April 2026.

OpenAI renamed Aardvark to Codex Security and opened a research preview to ChatGPT Pro, Enterprise, Business and Edu customers. OpenAI reports that in 30 days it scanned over 1.2 million commits in its beta cohort and flagged 792 critical and 10,561 high-severity findings, that beta changes cut false positives by more than 50%, and that its open-source reports led to 14 CVEs.

Anthropic released Claude Code Security as a limited research preview for Enterprise and Team customers, with expedited free access for open-source maintainers. The tool reasons about data flow across a codebase, re-examines each finding in a multi-stage verification pass, assigns severity and confidence ratings, and proposes patches that are applied only with human approval.

A systematization-of-knowledge paper by organizers and competitors analyzes AIxCC's design, the seven finalist architectures and results beyond the scoreboard. It reports that system stability and accuracy penalties decided rankings, that LLM-based systems found vulnerabilities a fuzzing baseline missed, and that among patches passing all automatic validation, manual review found semantic errors in 38-46% from baseline agents; the top two systems had 83.8% and 79.2% competition-scored patch accuracy.

Anthropic's Frontier Red Team reports that Claude Opus 4.6, run in a VM with standard tools but no custom harness, found and validated more than 500 high-severity vulnerabilities in open-source software, focusing on memory corruption that can be confirmed with sanitizers. Every bug was validated before reporting, initially by Anthropic researchers who also wrote patches and later with external researchers; examples include Ghostscript, OpenSC and CGIF.

OpenSSL's 27 January 2026 security advisory lists 12 CVEs, one High and one Moderate, all reported by researchers from Aisle Research, who also developed several of the fixes. AISLE states the issues were discovered by its AI system and that it accounted for 13 of 14 OpenSSL CVEs in 2025; the OpenSSL advisory itself credits the researchers but does not describe the discovery method.

OpenAI announced Aardvark, a GPT-5-powered agent in private beta that builds a threat model of a repository, scans commits, tries to trigger suspected flaws in a sandbox, and attaches Codex-generated patches for human review. OpenAI reports 92% recall on known and synthetically introduced vulnerabilities in its 'golden' repositories and ten CVEs from open-source scanning, and planned pro-bono scanning for some non-commercial projects.

Anthropic reports that a small team focused Claude Sonnet 4.5 training on finding and patching vulnerabilities and on testing simulated security infrastructure, while avoiding enhancements that clearly favour offence. It reports Sonnet 4.5 results on Cybench and CyberGym, a preliminary patching study in which 15% of patches were judged semantically equivalent to human references, and invites work on SOC and SIEM automation.

DARPA reports that seven finalist cyber reasoning systems analyzed over 54 million lines of code, found 54 unique synthetic vulnerabilities in 63 challenges and patched 43, and found 18 real non-synthetic vulnerabilities with 11 patches. Team Atlanta won $4 million, Trail of Bits $3 million and Theori $1.5 million; DARPA and ARPA-H added $1.4 million for real-world integration and four systems were open-sourced on the day.

Google's vice president of security announced that Big Sleep had reported 20 vulnerabilities, mostly in open-source projects such as FFmpeg and ImageMagick, with details withheld pending fixes. A Google spokesperson told TechCrunch each flaw was found and reproduced by the agent without human intervention, with a human expert reviewing reports before submission.

Google reports that, working from Google Threat Intelligence information, the Big Sleep agent found a critical SQLite memory-corruption flaw (CVE-2025-6965) that Google says was known only to threat actors and at risk of exploitation. Google says it reported the flaw for patching before attackers could exploit it, says it believes this is the first time an AI agent directly foiled an in-the-wild exploitation effort, and says Big Sleep is being applied to open-source projects.

BountyBench, from Stanford-led researchers, builds 40 bug bounties across 25 real-world systems into 120 Detect, Exploit and Patch tasks with dollar values attached. In the first version the best Detect score was 5%, while OpenAI Codex CLI and Claude Code scored 90% and 87.5% on Patch, well above their Exploit scores. A July 2025 revision with more agents reported Codex CLI with o3-high at 12.5% on Detect and 90% on Patch.

The NCSC's second assessment judges that AI will almost certainly make elements of intrusion more effective through 2027, with AI-assisted vulnerability research and exploit development the most significant development. It warns that the window between disclosure and exploitation, already days, will shrink further, and judges fully automated end-to-end advanced attacks unlikely before 2027.

Google reports that AI-generated and AI-enhanced fuzz targets in OSS-Fuzz found 26 new vulnerabilities in projects that already had extensive fuzzing, including CVE-2024-9143 in OpenSSL. The LLM workflow drafts targets, fixes compilation errors, fixes runtime issues and triages crashes, and gained coverage in 272 C/C++ projects.

Google Project Zero and Google DeepMind report that Big Sleep, an LLM agent evolved from Project Naptime, found an exploitable stack buffer underflow in SQLite during a variant-analysis experiment seeded with newly landed commits. The bug was reported in early October 2024 and fixed the same day, before it appeared in an official release; Google believes this was the first public example of an AI agent finding such a memory-safety flaw in widely used software.