Claude Code's background sessions survive terminal close, managed by a new supervisor daemon. We used it to build a persistent C2 agent whose entire payload is natural language in a Markdown file, executed by the signed binary under the user's identity.
https://t.co/1nD6ulkm03
Cloudflare's security team spent the last few weeks testing Anthropic's Mythos against fifty of our own repositories. What we learned about offensive AI, why faster patching is the wrong reaction, and what the architecture around vulnerabilities has to look like next. https://t.co/RSrRtIhgaV
@realhorsie Thanks for pointing that out. There was a bug in the binary fetcher so when I verified the output the hashes already matched the binaries I had. Should have double checked against Winbindex directly. The post has been updated.
One researcher. ~$300 in API tokens. A working PoC against an April Patch Tuesday CVE.
Open-sourcing PatchWatch + Pocsmith, an agentic patch-diffing → exploit pipeline I built from off-the-shelf parts.
https://t.co/J3VwhqB3JY
Last month we showed Claude Code's remote-control channel could be redirected to any server with one flag. Anthropic added a hardcoded domain allowlist as a fix. Because the allowlist lives in the client, the redirect still works. It just takes one more hop.
https://t.co/uwB27oqGkG
New on the blog: @michaelbarclay_ on the hidden supply chain behind every computer use agent. CLAUDE.md, skills, and MCP configs on disk compose its behavior at runtime, and a few lines in one of them can redirect a session in ways file telemetry can't see.
https://t.co/lBc6Q6p53o
Agent features don't need vulnerabilities to become tradecraft. They just need to be useful, installed, and exposed. Codex ships with a documented IPC surface for remote TUI sessions, and one bind flag turns a compromised endpoint into a remotely controlled agent.
https://t.co/uVulk48jqh
ACP standardizes how editors talk to coding agents. It also standardizes how an adversary on a compromised endpoint talks to those same agents - prompts invisible to command line logging, permissions auto-granted without the flags defenders look for.
https://t.co/dDlW3U2Sab
My research from last week on Claude Code's Remote Control protocol has landed in the latest release of Praxis C2 framework - try it out for yourself now!
https://t.co/rvXN2xPeQi
Process argument spoofing has focused on modifying the PEB before a suspended process resumes. @jdu2600 traces what happens after and finds the initialization timeline has its own injection windows - ones that fire after the allow decision has already been made.
https://t.co/DkgnCoOYQE
Claude Code's remote control protocol lets developers orchestrate instances programmatically. @tyholms reverse engineered it and found an undocumented flag that redirects any instance to attacker-controlled infrastructure, silently bypassing all permission checks.
https://t.co/Tn85uj1R77
Claude's Chrome extension lets the agent interact with the web on your behalf. We reverse engineered it and found those same capabilities are exposed to any attacker on the endpoint, turning a productivity tool into a browser takeover primitive.
https://t.co/Ah0XEje91I
Windows Insider builds now have a native, OS-level broker for MCP servers.
We reverse engineered Odr.exe to understand how it validates clients, manages consent, and controls access - uncovering undocumented COM interfaces and a full ETW audit trail.
https://t.co/8poGny9usX
Computer use agents like Claude Code are transforming endpoint interactions for humans - and potentially attackers too. Today, we're releasing cua-kit: a post-exploitation toolkit to explore their offensive security implications.
https://t.co/W4IAPWo3hL
While testing our agent against malware observed in the wild, we detected a LockBit encryptor not via file signatures or static IOCs, but by observing out-of-context execution of private memory using hardware telemetry. 🧵
Very excited to have joined the @originhq team just as big things were kicking off.
Kudos to the research team for this incredible work and can't wait to see where we go from here!