NEW: malware developers added nuclear & biological weapons text to to their spyware.
Goal? To trigger LLM safety refusals... so that their spyware wouldn't be analyzed by an AI security scanner.
Cleanest practical example I can think of for why over-indexing on first order safety alignment is risky.
When closed (and open) models ship with aggressive refusals, they will be sprinkled with second-order blindspots that attackers will discover...and exploit.
We are only in the earliest days of attackers leveraging these features, and it wouldn't surprise me if users systems that need to handle complex cybersecurity issues demand that models be less safety-blunted.
In the weeds: @SocketSecurity's post also shows why intention matters in how you design a malware analysis pipeline to avoid prompt manipulation.
H/T to colleagues that shared this with me https://t.co/f3Aj9TYxU4
Today, we are launching shift. Starting in NYC, we are bridging the economy of today into the AI economy where all services, goods, and leisure will be affordable, and humanity will progress towards abundance. Please enjoy your free home cleaning and join shift for a lot more!
Today we're open-sourcing Bumblebee, a read-only scanner for macOS and Linux.
It checks developer machines for risky packages, extensions, and AI tool configs.
Connected to Computer, it can trigger deeper scans whenever a new supply-chain risk emerges.
https://t.co/FOaWnF1yQy
@TheBlackHorse65 The AI call center that tries to fool you into thinking you are talking to a person can’t possibly last. Humiliation with a large attack surface
@JohnEDeaton1 plan is our fund setup a new LLC that owns exactly 49 single family homes and then passes the increased compliance costs onto tenants ? a win-win!
@oscpacey I hate to break it to you but all the large tech companies already offer law enforcement portals that provide everything legally available, front-door access
⚠️ BitUnlocker Attack on Windows 11 Allows Access to Encrypted Disks in 5 Minutes
Source: https://t.co/dq8KjmuHtP
A new tool, BitUnlocker, reveals a practical downgrade attack against Microsoft's BitLocker encryption, allowing attackers with physical access to decrypt protected volumes on patched Windows 11 machines in under 5 minutes by exploiting a crucial gap between patching and certificate revocation.
The attack is rooted in CVE-2025-48804, one of four critical zero-day vulnerabilities. Systems that have completed the KB5025885 migration, moving the boot manager signature to the newer Windows UEFI CA 2023 certificate, are also protected against this downgrade path.
#cybersecuritynews #Windows11