Cybersecurity Engineering Lead @Wayfair, #BlueTeam, @ISTatPENNSTATE Alum, @Babson MBA, Bostonian. Views are my own

Boston, MA
Joined February 2012
Mike Virginio retweeted
For the second time in Google Chrome’s history, Google awarded a $250,000 bounty for a full-chain exploit… to @XBOW. Here’s the full story: At an all-hands at the start of 2026 in Malta, I set the team a crazy challenge. A full-chain exploit of Chrome by the annual Black Hat cybersecurity conference in August. I believed there were few better tests of whether @XBOW could move beyond web applications to desktop software, servers and devices. Chrome is one of the most hardened pieces of software on the planet, used by more than half the world’s population. A full-chain exploit lets an attacker take total control of a machine, where they can read every email, password and bank login the user types. You don’t need to download anything or click a phishing link. Visiting the wrong site is enough. So @moyix, Andres Luksenberg, Baul Lee, and Willem Pinckaers took on the challenge along with a fifth teammate: OpenAI's GPT-5.6 Sol. They built a chain they thought would win, but Google told us they already knew one of the bugs. We were already in Las Vegas for Black Hat and DEF CON, and the team didn’t want to go home without the win. So Brendan and the agents built a new exploit in just 6 days. We submitted it to Google and waited. The news came through that we'd done what should’ve been impossible. A full-chain bounty of $250,000, the first awarded under Google’s 2026 rules. It took just 6 days and $40,000 of compute to construct an exploit that affects a billion users of Chrome on Windows. An intelligence-agency veteran told me his team used to spend 6 months on this kind of vulnerability. My takeaway: the cost of finding truly critical vulnerabilities is collapsing, for attackers and defenders alike. Restricting powerful models is not the answer; GPT-5.6 Sol is already public. But defenders have one advantage attackers never will: they can test their own code first. Assume your software is exploitable. Whoever is hunting your bugs has the same building blocks we did. This is cause for urgency but not panic. XBOW is now developing an autonomous product for testing compiled software (desktop applications, servers, embedded devices), and partnering with the world’s top organizations to design that product. If you’d like to be one of them, get in touch. P.S. Restart Chrome whenever the Update button appears!
87
263
97
2,615
815,949
Mike Virginio retweeted
We backdoored a 7B open model for under $50. Pointed Codex at it -> it silently stole credentials the moment we hit the trigger phrase. ->100% hit rate. -> zero false triggers on normal prompts. Abliterated models are all over the security community right now because getting cyber-approved access to frontier models is still a pain.
42
158
45
875
108,940
Mike Virginio retweeted
Once a month --> once a week --> every single day. Keeping up with new model launches is a full time job.
29
32
16
525
28,009
Mike Virginio retweeted
Sam Altman on Bloomberg Television: GPT-6 Astra is not the model that was paused over cybersecurity concerns; the paused model is a future model. "Astra has been done training for a while. The model that we recently talked about pausing, uh, is a future model. But with Astra, we did hit cyber-critical." ---- From "Bloomberg Television" YouTube channel, (full video link in comment)
65
142
61
2,119
519,059
Mike Virginio retweeted
Our Red Team tested GPT-6 on simulated cyber eval scenarios with cyber classifiers disabled and found that it performed a range of malicious actions. It tries to conduct supply chain attacks against simulated open source providers and goes beyond its scope to attack targets on the simulated internet. deploymentsafety.openai.com/…
Replying to @_robertkirk
1: Astra performed a range of malicious actions in this simulated eval, including conducting supply chain attacks against open-source providers. This happened even when we updated its scope to more explicitly exclude the public internet.
10
33
9
186
33,737
Mike Virginio retweeted
An open letter for a global surge in cyber defense, signed by over 100 organizations including Anthropic, AWS, Google, Microsoft, OpenAI, and Oracle.
411
686
381
3,963
1,421,637
Mike Virginio retweeted
Making your own D&D maps is easier than you think! 🗺️ Dungeon Scrawl is our free, browser-based mapmaker for creating old-school fantasy maps in minutes. Not sure how to start? Our latest tutorial covers everything you need to know! Learn to Scrawl: hubs.li/Q04sbRj00
4
22
2,716
Mike Virginio retweeted
Oooohkay let’s talk about this @OpenAI incident The @BlackHatEvents review board had questions. You all had questions and we put them to the OpenAI team to answer No fluff No marketing Just what in gods name happened
15
37
9
138
40,716
Mike Virginio retweeted
how can defenders get ahead of 100s of zero-effort prompts like "find vulns in file"? speedrun everything, all at once: agentic auditing loops, distilling variant patterns, coverage improvements. patch the planet
We’re expanding OpenAI Daybreak to help democratize patching vulnerable software at machine speed: - Codex Security plugin: find, validate, and fix vulnerabilities right inside Codex - The full version of GPT-5.5-Cyber model: a great model for trusted defenders - Cyber Partner Program: powering products built on top of our best cyber capabilities for leading security companies to secure the world's software - Patch the Planet: working with maintainers to secure critical open source projects openai.com/index/daybreak-se…
1
4
7
1,806
Mike Virginio retweeted
We benchmarked Fusion on 100 hard research tasks and found: 1. Panels of models consistently outperform individual models 2. Beyond-frontier performance can be achieved with frontier panels 3. Panels of budget models can surpass frontier models at a much lower cost
7
35
8
1,264
216,021
Mike Virginio retweeted
The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees. The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance. Access to all other Claude models is not affected. We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible. Read our full statement: anthropic.com/news/fable-myt…
12,187
25,095
28,880
86,806
93,488,483
Mike Virginio retweeted
New on the Engineering Blog: The access and permissions we grant agents should evolve with their capabilities. In our own products, we set these parameters through sandboxing, which limits the scope of any potentially destructive actions. Read more: anthropic.com/engineering/ho…
327
274
80
2,093
440,670
Mike Virginio retweeted
🔥 npm now requires human 2FA approval before staged package releases become installable — even from CI/CD workflows. thehackernews.com/2026/05/np… New package versions uploaded with staged publishing are placed into a queue and must be explicitly approved by a maintainer before release. Requirements: • npm CLI 11.15.0+ • 2FA enabled • Existing npm package • Use npm stage publish npm also added new install controls: --allow-file --allow-remote --allow-directory The updates are designed to strengthen defenses against software supply chain attacks targeting open-source ecosystems.
8
51
9
228
43,195
Mike Virginio retweeted
Exploitation mostly solved with Mythos/AI - what a run! >We see that current frontier LLMs, given a V8 N-day bug and its patch commit, can frequently demonstrate exploits that achieve useful primitives. Evaluations on private frontier models show that a fully end-to-end exploit against hardened targets, reaching arbitrary code execution from just the patch commit, is feasible under our defined turn budgets and simplified agent scaffolding. exploitbench.ai/blog/human-o…
3
10
70
12,732
Mike Virginio retweeted
For most of 2025, I was skeptical that AI was already playing a major operational role in real intrusions. Most public examples seemed limited to phishing and supporting tasks. This report by my friend Eyal Eyal lines up with what I have been hearing elsewhere, too - in recent publications and in private conversations with people seeing this stuff up close. I think that phase is over. AI is moving into the operational core of attacks. With stronger models, open models, and jailbroken variants circulating, the economics have changed. Tailored tooling, exploit adaptation, and large-scale analysis get cheaper and faster. I expect AI to play a major role in future campaigns, and that means more variation, more fresh tooling, and less reliance by attackers on recycled code. All the more reason to focus on controls and detections that do not depend only on known samples. Worth reading.
8
56
3
285
50,495
Does Anthropic delete the “earlier versions” of Mythos? What happens if this source code is leaked?
Mythos Preview seems to be the best-aligned model out there on basically every measure we have. But it also likely poses more misalignment risk than any model we’ve used: Its new capabilities significantly increase the risk from any bad behavior. 🧵
1
1
119
Mike Virginio retweeted
Mythos Preview seems to be the best-aligned model out there on basically every measure we have. But it also likely poses more misalignment risk than any model we’ve used: Its new capabilities significantly increase the risk from any bad behavior. 🧵
52
181
60
1,394
987,220
Mike Virginio retweeted
Introducing Project Glasswing: an urgent initiative to help secure the world’s most critical software. It’s powered by our newest frontier model, Claude Mythos Preview, which can find software vulnerabilities better than all but the most skilled humans. anthropic.com/glasswing
1,935
6,527
4,419
43,435
31,964,425