AI
MCP for agent-to-agent comms may be the riskiest protocol you’ve never heard of
Skip to content Trust gaps in the new protocol spread malicious prompts from one agent to another. The adoption of AI agents…
Apple changes full-disk access permissions to curb abuse from AI agents
Apple says it is changing its macOS privacy settings to stop third-party app developers from misusing them to access message histories. Friday’s…
Smashing Security podcast #486: Vibe-coded shops, and hackable Flock cameras
DAVE BITTNER I have to say, what this reminds me of is there was a glitch on Amazon for a while. I…
Microsoft disrupts AI-assisted platform that compromised 12,000 accounts
Microsoft said Tuesday that it led an industry-wide disruption of a subscription-based scam platform that used an AI chatbot to compromise 12,000…
Muse, Meta’s extraordinarily privileged AI assistant, has a serious 0-day
A simple ClickFix attack is only one way to completely hijack the new agent. Meta founder and CEO Mark Zuckerberg has gone…
Researchers used Claude to hack OpenAI
They exploited a flaw in the set-up of OpenAI’s community forum, which is hosted by a third-party, Discourse, and used it to…
LLMs respond differently to harmful prompts when AI watermarking is used
Standard versus watermarked text generation. Credit: Lasso Security Standard versus watermarked text generation. Credit: Lasso Security A key feature of SynthID is…
Smashing Security podcast #485: These researchers got drunk to hack an LG TV
RESEARCHER So we’re gonna have a private conversation about our next crypto scam, and it would really be unfortunate if anyone had…
Smashing Security podcast #483: This AI helps thieves steal your iPhone
JAMES BALL At what stage was this surprise? You know, we locked 15 murderers in a room. You’ll never believe what happened…