lugapelsiteadmin
Just like phishing for gullible humans, prompt injecting AIs is here to stay
Aren't we all just prompting tokens of linguistic meaning and hoping the other person isn't bullshitting us? kettle It's a week of the year, which means there's been the discovery of yet another prompt injection attack that will force supposedly well-guarded AI bots to spill secrets by asking…
I meant to do that! AI vendors shrug off responsibility for vulns
Passing the buck, and the blame, down the road shows lack of AI companies' maturity OPINION AI vendors: "You need to use AI to fight AI threats (and do everything else in your corporate IT environment)." Also AI vendors: "That's not a security flaw; it's working as intended."…
CISA tells feds to patch 13-year-old Apache ActiveMQ bug under active attack
Bug hiding in plain sight for over a decade lands on KEV list CISA is sounding the alarm on a newly-exploited Apache ActiveMQ bug, ordering federal agencies to patch within two weeks as attackers circle a flaw that's been quietly lurking for more than a decade.…
Opsec oopsie: Dutch navy frigate location outed by mailing it a Bluetooth tracker
Or, how public information and a €5 tracker exposed an avoidable opsec lapse Militaries around the world spend countless hours training, developing policies, and implementing best operational security practices, so imagine the size of the egg on the face of the Dutch navy when journalists managed to track…
Locked-out iPhone user tells The Reg that Apple is scrambling to fix character flaw passcode bug
University student says he plans to move to Android, but concedes iOS engineers acting fast Apple is finally working on a fix for a bug that has locked some users out of their iPhones for months, The Register understands.…
Claude Opus wrote a Chrome exploit for $2,283
Pause your Mythos panic because mainstream models anyone can use already pick holes in popular software Anthropic withheld its Mythos bug-finding model from public release due to concerns that it would enable attackers to find and exploit vulnerabilities before anyone could react.…
Anthropic won’t own MCP ‘design flaw’ putting 200K servers at risk, researchers say
Bug or feature? A design flaw – or expected behavior based on a bad design choice, depending on who is telling the story – baked into Anthropic's official Model Context Protocol (MCP) puts as many as 200,000 servers at risk of complete takeover, according to security researchers.…
Americans who masterminded Nork IT worker fraud sentenced to 200 months behind bars
Fortune 500 companies and one US defense contractor got taken for $5m in four-year scam Two Americans have been jailed for a combined 200 months for helping North Korea generate $5 million through fraudulent IT worker schemes.…
Git identity spoof fools Claude into giving bad code the nod
Forged metadata made AI reviewer treat hostile changes as though they came from known maintainer Security boffins say Anthropic's Claude can be tricked into approving malicious code with just two Git commands by spoofing a trusted developer's identity.…
Textbook titan McGraw Hill on ransomware crew’s reading list after 13.5M records exposed
Publisher claims misconfigured Salesforce-hosted page leaked data Textbook giant McGraw Hill has landed on a ransomware crew's leak site after an alleged Salesforce-linked misconfiguration spilled 13.5 million records into the wild.…