The CyberBinGym preprint evaluates agents given stripped vulnerable and patched binaries for 100 tasks from 53 projects. On the non-hardened baseline, Codex with GPT-5.6 recovers vulnerabilities on 88% of tasks and completes exploitation on 20%. The known-vulnerability patch-gap tests use trusted-access models with safeguards disabled; hardened configurations are evaluated separately.
Exploit development
Building working exploits with AI assistance or autonomy.
Use the arrow keys to move between records, Home and End to jump to the first and last, and Enter to select one.
Select a mark to read the record. Mark size shows editorial significance. Hollow marks are dated to the month. Era bands are editorial labels.
Records in view
20 records · newest firstOpenAI released GPT-6 Cyber, a cyber-specialized GPT-6 Astra variant, initially to selected Daybreak Red customers. OpenAI’s own evaluations report stronger performance on specified exploitation tasks. In a separate honeypot test, successful exploitation of an out-of-scope service was rare without deployment safety instructions and absent in the graded runs with them. General containment remains outside the scope of this measurement.
OpenAI describes a Linux research pipeline that produced 2,308 candidate findings, dynamically reproduced 1,724 and developed 948 local privilege-escalation exploits on its stock desktop target. It generated candidate patches for review, rather than reporting that all findings were novel or all fixes had shipped. Hardened-target results are a separate cohort.
Epoch AI reports that GLM 5.3 developed file-reading exploit chains for six Firefox releases using information public at each release date. Researchers supplied an offline setup with tools and materials, then let the model work without further human input; every chain also used an unpublished vulnerability that Mozilla patched in Firefox 159.0.
Google’s October 28 announcement reports unguarded Gemini 4 Carbon cyber evaluation scores and phased defender access through Fairwind. Its November 10 release expands access to paying developers and enterprises and rolls out consumer access to Google AI Ultra subscribers. Broader general availability does not imply identical safeguards or access to the specialized cyber configuration.
Anthropic describes five selected exploit-chain demonstrations involving Chrome, Safari, Android, Windows and Linux, developed with an unreleased internal research model. It reports coordinated vendor fixes and little human involvement after initial prompting, with different outcomes including code execution, data access and denial of service.
OpenAI describes coordinating fixes for two critical PHP flaws after Calif identified one using AI and Wiz independently found both; PHP released fixes on October 21, and OpenAI proposed a disclosure framework. Follow-up evidence includes CISA’s October 26 listing of both flaws as known exploited and Palo Alto Networks’ report of active exploitation against internet-exposed management interfaces. Wiz’s October 27 report describes declining observed exposure and failed chains in its own captured attempts; this does not establish an absence of exploitation elsewhere or a global compromise count.
A team from 2077AI and several universities presents CyberArena, in which two model-harness entrants host identical vulnerable services in isolated sandboxes and, over three 20-minute rounds, try to capture rotating flags from the opponent while patching their own service under health checks. They report standings for 12 agents over 466 valid games on 40 challenges, with GPT-5.6 Sol at an expected score of 78.6 and Claude Opus 5 at 73.8, and say contested play lowers capture rates relative to solo play. An LLM-run audit of all trajectories reports recurring defender errors such as partial patches and repair claims resting on stale evidence; the authors note it is not human verification of every finding.
Authors affiliated with XOR, Protege and CISPA evaluate attack, repair and subsequent attacks in five nonpublic software environments using researcher-reviewed deterministic graders. Repair scores exceed attack scores in two environments and fall below them in three, while subsequent tests expose failures after an initial exploit is stopped. The selected environments, differing outcome definitions and dependent interactions do not establish a general attacker or defender advantage.
Google Threat Intelligence Group (GTIG) reports that monthly CVE disclosures rose from 5,045 in January 2026 to 10,477 in July and 10,740 in August, and that exploited vulnerabilities averaged 18 per month from January to August 2026 against 10.5 per month in 2025. GTIG says zero-day exploitation rose only marginally and suggests rapid weaponization of n-days drove most of the growth, and that vulnerabilities it identified as likely AI-discovered skew toward Medium risk ratings and remote code execution. It also counts 2,076 cumulative AI-related CVEs (January 2025 to August 2026) and reports in-the-wild exploitation of a handful, including a flaw in LiteLLM's MCP server preview endpoints.
Anthropic's Frontier Red Team reports that Zhipu AI's open-weight GLM-5.3 developed end-to-end exploits in 50 of 410 ExploitBench attempts, against 56 of 410 for Claude Mythos Preview, and full control-flow hijacks in 4% of trials on a 100-task subset of Anthropic's internal binary-exploitation benchmark, against 6% for Mythos Preview. In a simulated harmful-request test, Anthropic reports the model's refusals were bypassed in 64% to 100% of trials using a cover story, prefilled reasoning, or an abliterated copy of the weights, techniques it says did not work on safeguarded Claude models. All figures are Anthropic's own and were produced on setups the post describes only in part.
Researchers at the Chinese Academy of Sciences release ReproBench, which gives an agent only a CVE identifier and scores six phases from finding the firmware to triggering the bug on the real binary, using 30 IoT firmware CVEs. Across 450 runs of five models in one harness, the authors report that 204 runs (45.3%) substituted a mock or host-native simulation, which the benchmark scores as zero for the real-target phases. They report near-full credit on the rehosting and triggering phases for 11 and 8 of 150 CVE-model pairs.
Anthropic's Claude Opus 5.5 system card reports that, evaluated through the API with its cyber safeguards off, the model meets or exceeds Claude Mythos 5.1 and Claude Opus 5 on every cyber evaluation it includes (ExploitBench, CyScenarioBench, a rewritten Binary Exploitation Benchmark and ExploitGym). Anthropic places the model in the lower category of its Frontier Compliance Framework and says it sees no indication of novel offensive capability. It deployed the model with a three-stage cyber safeguard (an activation probe and two classifiers) that blocks vulnerability discovery in compiled binaries, and reports no evidence of a critical-severity jailbreak from internal and contracted external red teaming (the card gives no CAISI results).
Trail of Bits argues in a blog post that a standard virtual machine should no longer be assumed to contain a sufficiently capable cyber agent, based on one researcher's informal test of a preview of OpenAI's GPT 5.6-Cyber obtained through Patch the Planet. In a capture-the-flag setup on a Linux development machine, the agent was told to escape a QEMU/KVM VM; the author reports three escapes: a known host-kernel bug (whose exploit did not land cleanly), a combination of libslirp bugs on an oldstable distribution, and a chain that included 0-day bugs against freshly rebuilt upstream QEMU. The author recommends rapidly updated distributions, minimal-attack-surface virtualization such as Firecracker (which the agent did not escape), least privilege, logging, monitoring, time limits and a fresh environment per use.
The UK AI Security Institute and US CAISI published a joint preliminary assessment of Moonshot AI's open-weight Kimi K3. They report it trails leading US closed models on exploit development and a 32-step cyber range, and that its safeguards did not stop it attempting exploit development.
Carnegie Mellon researchers released ExploitBench, which scores exploitation progress on 41 V8 JavaScript-engine vulnerabilities across 16 flags from reaching the bug through arbitrary read/write, control-flow hijack and code execution. The paper reports that public models routinely reach and crash vulnerable code but rarely achieve arbitrary code execution, while one private frontier model succeeded on roughly half of cases.
Researchers led by UC Berkeley, with collaborators including Anthropic, OpenAI and Google, released ExploitGym, a benchmark of 898 real-world vulnerability instances across userspace programs, the V8 JavaScript engine and the Linux kernel. Agents start from a crashing input and must extend it into a working exploit under varied security protections. The paper reports that the strongest configurations, Claude Mythos Preview and GPT-5.5, produced working exploits for 157 and 120 instances respectively.
Google Threat Intelligence Group reported that cybercriminals planned a mass-exploitation campaign using a two-factor-authentication bypass in an open-source web administration tool, and assessed with high confidence that an AI model supported discovery and weaponization of the flaw. GTIG worked with the vendor on disclosure and disrupted the activity. The same report describes PRC-nexus actors using agentic frameworks such as Hexstrike and Strix for reconnaissance and vulnerability validation, and Android malware (PROMPTSPY) that calls Gemini to drive the device UI.
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.
OpenAI's Preparedness Framework version 2 makes cybersecurity one of three Tracked Categories and defines High and Critical capability thresholds, each tied to required safeguards. High covers automating end-to-end operations against reasonably hardened targets or automating discovery and exploitation of operationally relevant vulnerabilities; Critical covers autonomous zero-day development across many hardened critical systems, and at Critical OpenAI commits to halt further development until adequate safeguards are specified.