Tag: AI security
Eight hundred hacking agents sat open and nobody noticed
Censys found more than 800 Artex deployments reachable from the open internet with no password required.
CrowdStrike buys two agent monitors and ships a kill switch
Fiddler and Dreadnode would give Falcon a flight recorder and an attack simulator for autonomous agents, alongside a…
Google’s bug-hunting agent only reports what it can prove
A Gemini-powered security agent at Google has surfaced more than 500 cross-site scripting flaws with a near-zero false-positive…
Cohere says a Qwen model reached for a server in Beijing
The Canadian lab published raw traces after its sandbox blocked an unexpected file upload during a security test.
Anthropic opens the sandbox it uses to cage Claude Code
The tool leans on macOS Seatbelt and Linux bubblewrap to wall off files and networks without shipping a…
AI turned a decade-old PHP flaw into a working exploit
PHP2Shell drew millions of attack attempts within hours, and the vulnerabilities behind it were already known to maintainers…
Anthropic says a newer internal model walks away from attacks
After Claude Mythos 5 pushed malware at a real GitHub project, Anthropic replayed the run against other models…
An AI model found a PHP flaw before attackers did
A researcher inside OpenAI's Patch the Planet programme used GPT-5.6 Sol to trace an exploit chain that nobody…
Perplexity open-sources SPACE, a sandbox that walls agents off
SPACE isolates each agent in its own walled-off cloud machine, and the company says the escape incidents of…
Bank of America spent $200M-plus patching AI-found flaws
Its CEO says 1,000 contractors joined an existing 3,000-person team after frontier models exposed old code.
OpenAI engineer charged with planting a bug in a boardroom
US prosecutors say an OpenAI staffer hid a recording device in a conference room used for leadership meetings…
AI bug hunting is already flooding the patch pipeline
Vulnerability disclosures have doubled year over year, and the people who must fix them are not scaling.