# Patch the Planet Published articles for Patch the Planet. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Review argues 1Password's AI patching benchmark overstates poor patch quality DevFeed: [Review argues 1Password's AI patching benchmark overstates poor patch quality]() Original publisher: [Read original article]() Author: "Anish Naik"; "Dan Guido"; "Benjamin Samuels"; "Marcelo Morales" Published: 2026-09-15T11:00:00Z Content type: opinion Language: en Sources: [The Trail of Bits Blog](), [The Trail of Bits Blog]() Topics: [Artificial Intelligence](), [Benchmark](), [Vulnerabilities](), [Testing](), [Agent Skills]() Tags: [agent-skills](), [agents](), [ai](), [benchmark](), [open-source](), [patch-the-planet](), [report](), [testing](), [vulnerabilities]() ### AI overview The article argues that 1Password's 26% clean-fix headline gives a misleading picture of AI patching because the benchmark included difficult vulnerabilities, prompts instructing agents to apply wrong fixes, trials that prohibited testing, and differing reasoning settings. It reports that 2,634 of 3,067 eligible patches blocked the supplied exploit and announces two agent skills for validation and review. ### Source excerpt 1Password's FLAWED report, published on August 6, 2026, gives defenders a misleading picture of AI patching. Its headline says models produced clean fixes only 26% of the time. That figure includes experiments that deliberately instructed agents to apply the wrong fix, along with experiments in which agents could not compile or test their patches. The report risks making defenders less effective by discouraging them from using technology that could help them fix more vulnerabilities. Teams that take its headline at face value may leave repairable vulnerabilities unaddressed. We want our work to help defenders fix more vulnerabilities. This post shares real-world data on human and agent patch quality from our consulting projects and Patch the Planet. We're also releasing two agent skills: post-patch-validation to help agents test fixes, and review-walkthrough to help engineers review them. How the experiment produces a misleading headline Our review of 1Password's code and data found four choices that make its 26% clean-fix rate a misleading guide to ordinary patching work.1 The sample was selected for difficult fixes. The authors chose six vulnerabilities because their fixes were complex. Clean-fix rates ranged from 3% to 60% across those bugs, so the average depends heavily on which vulnerabilities made the list.2 Two prompts tell agents to apply the wrong fix. Those prompts account for 22% of the data. Combining them with ordinary repair attempts makes the reported rate depend partly on how often the researchers chose to give agents bad advice. More than a third of the trials prohibit testing. One evaluation mode prevents agents from building or running code and accounts for 36% of the data. The headline combines those trials with experiments in which agents could test their patches and act on the results. The models ran at different reasoning settings. GPT-5.5 ran at medium effort and Opus 4.8 at high. These were the tools' defaults. Neither model was tested at i ## VMs won't contain cyber-capable agents DevFeed: [VMs won't contain cyber-capable agents]() Original publisher: [Read original article]() Author: "Artem Dinaburg" Published: 2026-08-26T11:00:00Z Content type: article Language: en Sources: [The Trail of Bits Blog](), [The Trail of Bits Blog]() Topics: [Vulnerabilities](), [AI Bots](), [AI-assisted coding]() Tags: [ai](), [ai-agent](), [bugs](), [cybersecurity](), [gpt](), [kernel](), [linux](), [open-source](), [patch-the-planet](), [vulnerabilities]() ### AI overview An evaluation of GPT 5.6-Cyber reports that it escaped a QEMU/KVM sandbox three times by using disclosed flaws and finding zero-days. The article argues that capable autonomous AI agents should not be assumed to be safely contained by a VM. ### Source excerpt As part of Patch the Planet, we received preview access to GPT 5.6-Cyber with a simple task: evaluate its cyber capabilities. Recent events inspired me to give it a challenge to work through: escape the VM I'd normally use for sandboxing. The target was a QEMU/KVM VM on my Linux dev machine (Debian Linux 12, AMD Zen3). It escaped the VM three different times. First, it used recently disclosed bugs in my host kernel. When I fully updated, it used disclosed bugs that had not yet reached package maintainers or were not classified as security bugs. When I rebuilt QEMU and dependencies from the latest upstream source, it found several 0-days. It operated autonomously for hours, backtracked from approaches that didn't work, pulled code and research papers, wrote oracles, made its own minimal examples, and aimed for a reusable, reliable exploit, all with minimal handholding and prompting. My main job was to physically reboot the machine when it hardlocked the host kernel. If it wasn't clear before, I will state it plainly: you can no longer assume a mere VM will contain a sufficiently advanced AI agent. To use a 2010s term of art, you should treat such agents as an advanced persistent threat. Advancing cybersecurity capabilities Let's imagine a common situation: you want to run an AI agent, but need its full capabilities, including the ability to download, build and debug software; do research; sift through dependencies; set up fuzzers; triage vulnerabilities; and stand up services under different configurations. The generally accepted solution is to set up a VM that serves as a safety perimeter and isolated prison for the agent: this virtual environment contains nothing of value, is separate from the host, and can be immediately deactivated or snapshotted for later investigation. This setup allows the agent to roam free, while isolating your computer from its consequences. There is, of course, a tiny wrinkle. To be useful, the virtual environment must share resources with ## How we use /goal to find bugs in Patch the Planet DevFeed: [How we use /goal to find bugs in Patch the Planet]() Original publisher: [Read original article]() Author: "Trail of Bits" Published: 2026-07-28T11:00:00Z Content type: article Language: en Sources: [The Trail of Bits Blog](), [The Trail of Bits Blog]() Topics: [codex](), [bug](), [Open Source](), [open-source-security](), [cURL](), [Rust](), [OpenAI]() Tags: [analysis](), [blog](), [bugs](), [code](), [codex](), [machine-learning](), [open-source](), [openai](), [patch-the-planet](), [software](), [tool](), [vulnerabilities]() ### AI overview The article describes how Trail of Bits used Codex's /goal feature in Patch the Planet to find bugs in open-source software. It highlights results involving Rust, curl, Semgrep-based variant analysis, and potential Keycloak privilege-escalation issues, then discusses goal and prompt design techniques. ### Source excerpt Codex's /goal feature amplifies bug hunting, but getting good results requires the right prompt, the right scope, and the right number of outcomes per run. For Patch the Planet, our joint initiative with OpenAI to find and fix bugs in open-source software, we pointed Codex at some of the most widely used, heavily audited codebases in the world, like Rust, curl, and zlib. One tool came up again and again in our internal bug-report channels: /goal, which hands Codex an open-ended objective and lets it work independently toward a success condition. Here are a few highlights: /goal found every Rust bug we submitted, including a soundness hole and a miscompilation now patched in Rust 1.98, from a single variant-analysis pipeline. It turned every project's past CVEs into Semgrep rules that had to fire on the vulnerable version and stay silent on the patched one, then flagged 11 variant hits across multiple projects. It uncovered two potential high-severity privilege-escalation bugs in Keycloak's SAML component during a discovery run. Over the first few weeks of Patch the Planet, our engineers independently converged on three techniques for using /goal. We found that getting the most out of /goal means treating the prompt as a set of specific success criteria, not a set of instructions. (Note that this blog post uses /goal to refer to goal-based prompting in general. Codex can also set goals for itself through a tool call, and that's how we recommend everyone use it; we rarely type the slash command ourselves.) 1. Let Codex write the goal The art of using /goal is prompt design, and we found that Codex knows Codex the best. Internally, our single most repeated /goal tip was to use Codex to help write each /goal prompt. We hand Codex threat model files and the context about what we're looking for, and then tell it to write the goal prompt. As mentioned before, /goal is a tool Codex can invoke on itself, and a few engineers stopped typing goals by hand entirely. $goal-prompt ## GPT-5.5-Cyber built a zlib fuzzing lab in a day DevFeed: [GPT-5.5-Cyber built a zlib fuzzing lab in a day]() Original publisher: [Read original article]() Author: "Benjamin Samuels" Published: 2026-07-02T11:00:00Z Content type: article Language: en Sources: [The Trail of Bits Blog](), [The Trail of Bits Blog]() Topics: [AI-assisted coding](), [Vulnerabilities](), [AI Chat]() Tags: [bugs](), [codex](), [compression](), [fuzzing](), [gpt](), [machine-learning](), [open-source](), [openai](), [patch-the-planet](), [security](), [tooling](), [vulnerabilities]() ### AI overview Trail of Bits reports that GPT-5.5-Cyber built a fuzzing campaign for zlib in a day, using sanitizer and variant builds, harnesses, and seeds. The effort is part of Patch the Planet, which aims to find and patch security bugs in open-source projects with maintainers. ### Source excerpt We're running Patch the Planet, an ongoing collaboration with OpenAI that pairs Trail of Bits engineers directly with more than 30 open-source projects. Its goal is to front-run a serious problem facing open-source maintainers: highly capable models like GPT-5.5-Cyber will soon create a firehose of bug reports, and OSS maintainers are already spread thin. Our plan is to point OpenAI's latest models at real codebases, find the security bugs first, work with maintainers to patch them, and find ways to decrease the burden on maintainers in the long run. We'll publish field reports like this one as the initiative progresses; follow along via the Patch the Planet tag. The expertise barrier that kept bespoke fuzzing campaigns out of reach for most attackers is gone. We watched GPT-5.5-Cyber build in a single day what would have taken weeks for a skilled security researcher: harnesses across a dozen entrypoints, sanitizer and variant builds, seeds, and multiple findings currently undergoing coordinated disclosure. This particular instance focused on zlib, a widely used data format and lossless data compression software library. We pointed GPT-5.5-Cyber at the library and drove it through Codex with the /goal command, asking it to find a specific class of bugs that are critically dangerous in compression libraries. We'll publish the full harness and findings for inspection once the vulnerabilities are patched and a new release is cut. The lab GPT-5.5-Cyber built in a day We didn't tell the model how to find these bugs. The obvious first move is to read the source code, but zlib has been reviewed so thoroughly that there's little left to find that way. GPT-5.5-Cyber worked that out for itself, judged static review to be a poor use of tokens, and decided the higher value path was to build fuzz tooling to dynamically test the code. Earlier models given the same goal tend to read the code and flag whatever looks suspicious, ultimately leading to mediocre outcomes. We believe th ## Introducing Patch the Planet DevFeed: [Introducing Patch the Planet]() Original publisher: [Read original article]() Author: "Trail of Bits" Published: 2026-06-22T16:50:00Z Content type: article Language: en Sources: [The Trail of Bits Blog](), [The Trail of Bits Blog]() Topics: [Open Source](), [Security](), [Vulnerabilities](), [Maintainers](), [pull-requests](), [Fuzzing/Fuzz testing](), [GitHub](), [Cryptography](), [networking](), [cURL](), [Go Language]() Tags: [announcements](), [cryptography](), [fuzzing](), [github](), [github-actions](), [go](), [maintainers](), [networking](), [open-source](), [openai](), [patch-the-planet](), [pull-requests](), [security](), [supply-chain](), [vulnerabilities]() ### AI overview Patch the Planet pairs Trail of Bits engineers and open-source maintainers with frontier models to discover, triage, and fix security issues. Its first week produced hundreds of bugs, 64 pull requests, and 51 issues across 19 projects, with work also adding tests, fuzzing harnesses, CI security scanning, supply-chain tooling, correctness fixes, and features. ### Source excerpt What happens when you clear dozens of Trail of Bits engineers' schedules, pair them with every open-source maintainer they can contact, and unleash the latest frontier models like GPT-5.5-Cyber on critical open-source targets? Thanks to our partnership with OpenAI and its Daybreak initiative, we can report that the impact is hundreds of discovered bugs, 64 pull requests, and 51 issues filed across 19 projects (with many more still undergoing coordinated disclosure). That was just the first week of Patch the Planet. Frontier models like GPT-5.5-Cyber are producing a firehose of security findings, and already-stretched maintainers must sift through all of it to separate real vulnerabilities from plausible-sounding false positives. Patch the Planet is different: with our experts orchestrating and triaging findings, we handle the work of fixing and hardening the code alongside the people who maintain it. The first week of Patch the Planet covered 19 projects across cryptography, networking, language infrastructure, and software supply chain. Among these 19 projects were cURL, NATS, pyca, Sigstore, aiohttp, the Go project, freenginx, Python and python.org, urllib3, PyPI, SimpleX, Valkey, and RustCrypto. Over 30 projects have joined the initiative so far, and we're rapidly expanding it to include more; if you maintain an open-source project, apply to join! Live look at the Trail of Bits engineering teams Anyone can file an issue, flex, and walk away. We showed up with the patches: 37 are already merged, and many more are in flight. These merges go beyond just fixing bugs: we're adding new tests and fuzzing harnesses, CI security scanning, supply-chain tooling, correctness fixes, and features maintainers had been meaning to get to. The goal of Patch the Planet is to leave essential open-source projects measurably better off. We brought patches, not just bug reports We're reporting public findings on GitHub, including 64 total pull requests. We also filed 51 issues, 19 of w ## Patch the Planet: a Daybreak initiative to support open source maintainers DevFeed: [Patch the Planet: a Daybreak initiative to support open source maintainers]() Original publisher: [Read original article]() Published: 2026-06-22T10:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [Vulnerabilities](), [open-source-security](), [AI-assisted coding](), [CI/CD]() Tags: [ai](), [ci-cd](), [codex](), [maintainers](), [open-source](), [patch-the-planet](), [review](), [security](), [vulnerabilities]() ### AI overview Patch the Planet is a Daybreak initiative that combines AI-assisted security research with expert review to help open-source maintainers validate vulnerabilities, develop patches, test fixes, and coordinate disclosure. ### Source excerpt OpenAI introduces Patch the Planet, a Daybreak initiative helping open-source maintainers find, validate, and fix vulnerabilities with AI and expert review. ## Daybreak: Tools for securing every organization in the world DevFeed: [Daybreak: Tools for securing every organization in the world]() Original publisher: [Read original article]() Published: 2026-06-22T10:00:00Z Content type: release Language: en Sources: [OpenAI News]() Topics: [Vulnerabilities](), [AI-assisted coding](), [AI Chat]() Tags: [ai-models](), [codex](), [collaboration](), [frontier-ai-models](), [go](), [gpt](), [kernel](), [linux](), [open-source](), [openai](), [patch-the-planet](), [python](), [security](), [tools](), [vulnerabilities]() ### AI overview OpenAI announces Daybreak tools aimed at helping defenders discover, validate, and patch software vulnerabilities at scale, including Codex Security and GPT-5.5-Cyber. ### Source excerpt OpenAI introduces new Daybreak tools, including Codex Security and GPT-5.5-Cyber, to help organizations find, validate, and patch vulnerabilities at scale.