Vivek R

CVE-2026-112512! We discovered a 0-day in macOS that lets you trivially bypass Gatekeeper checks for any app. A gatekeeper bypass that requires no extra interaction, with quarantine bit intact, and passes the Safari download flow. Essentially checks off all the criteria required for a complete Gatekeeper bypass on macOS, which according to Apple is worth $100K? We shall wait and see. Will def do a write-up on this soon!

I have been thinking about "AI defense" and "safeguards" for a while now @winfunction. Just wrote an essay to put my thoughts into words. Titled: Cyber guardrails tax the defender, not the attacker. Link in the replies.

Introducing ENDGINX - 5 CVEs in NGINX with open models. We let loose GLM 5.1 and 5.2 by @Zai_org on the NGINX codebase. The work resulted in six fixed vulnerabilities across five CVEs: CVE-2026-28755, CVE-2026-42926, CVE-2026-9256, CVE-2026-42055, and CVE-2026-42533. First of our open-model vulnerability research series. winfunc.com/research/endginx

another one! all of these are discovered with open models btw. the blog will be published after all the findings are properly disclosed so we can talk about them in detail. there's a specific pattern to the kind of vulns these open models find, it's interesting! chromereleases.googleblog.co…

one of them has been disclosed with a CVE. more to come. besides, what’s google cooking? mythos? their own gemini variant? interesting times. chromereleases.googleblog.co…

We discovered the same vulnerability too. :) And @winfunction discovered 4 more remote RCE primitives in NGINX soon to be publicly disclosed. Anywho, we're hiring security researchers with a knack on taming LLMs. If you're interested in novel vulnerability research and autonomous exploitation with language models, DM me and I'll send you a fun CTF to solve. :)

We're doing an experiment with open models @winfunction to see how far we can push them to find vulns in hardened targets. So far: - $4.5K in bounties from Chrome VRP with a few more pending, with the scans costing less than $100. - 2 CVEs in NGINX (CVE-2026-28755 & CVE-2026-42926). And watch out for the next release! - And 60ca500faea0fc70816bb9c53af3815e2af3e6c962b4b4ea63c33c62ebb4240d 👀 We're writing a blog on this soon.

Love the Claudia reference as the first thing here. We loved working on Claudia but couldn't balance working on security research projects and Claudia at once. Fun fact, we invented "SKILLS" before it was even a thing. There was a feature in Claudia called "AGENTS" where users could share and install system prompts for specific tasks via their GitHub repos, just like the skill marketplaces concept in Claude now. See here: github.com/winfunc/opcode/tr… And Anthropic did talk to us after the launch of Claudia but unfortunately I can't reveal more about it but damn was it some tough decision.

these models are really good at pattern matching and thereby variant analysis. “iterate through security fix commits and find similar vulnerabilities / unpatched areas of the same variants. write runnable pocs for valid ones.” is enough to uncover surface-level or even P0 vulnerabilities in a codebase with the latest models. i believe for proof of cyber capabilities, these models should exhibit discovery of novel attack vectors that requires understanding of runtime behavior with and without tooling? like emulating the runtime in CoT/reasoning? for instance, the react2shell vulnerability was ingenious. without stuffing in context and nudging/handholding (ehem like some experiments going on), can these models find a similar attack vector with a prompt like “loop until you find a p0/critical security vulnerability”? that’s what i’d like to see. these models can claim P0 findings with contractual mismatches for say cryptographic implementations but the impact could just be some DoS that’s being prevented by a parent thread. this is where i see the moat with good harnesses. trust-boundary and threat model understanding, a sandbox environment with the right “win function” for pocs to run on (if xyz happens, it’s a valid vuln), etc. does make the models spit out impressive vulns. this is sort of what we do @winfunction. cus most vulnerabilities are easily traceable given a comprehensible source-to-sink flow which these models have been good at for a long while now. and with respect to exploit dev, i strongly believe it’s mostly a tooling problem. with the right tool calls and model digestible outputs of say tracing tools, memory layout, syscalls, threads/processes, and a debugger interface, i think the frontier models can pull off complex multi-chain exploits. (we have run some experiments here and the models are not too bad at this) security vulnerabilities have a definitive “win function”, like a flag in a ctf, like popping a calc, like ASAN crashes, like `id` says root, like +1000 in milliseconds. this makes the problem very RL verifiable. so i only expect the harness to get leaner. the harnesses will get leaner. remember when function calls where part of the response content? we called it “prompt based tool calling” and now there’s typed/schema based tool calling as an inherent capability of these models. most of what we call a harness or an agent is giving the right prompts and the right tools (which are also just prompts). so whoever can weave the right sequence of tokens to these behemoth of language models can hoard zero days or spit them out. so git gud at feeding the right tokens at the right time ig.