SecurityWeek

Prompt Injection Attacks Trick AI Agents Into Making Crypto Payments

Zscaler found attackers using SEO poisoning and hidden prompts in malicious websites to manipulate AI agents into making cryptocurrency payments.
Tech Times

New APT Group Hits Power Grids in Three Countries with AI-Crafted Malware

Armored Likho BusySnake Stealer, a Python-based infostealer first disclosed by Kaspersky, is actively targeting government ...
TweakTown

Security researchers trick AI browsers into revealing passwords using BioShock-inspired prompt injection

Named after BioShock's 'Would you kindly' mechanic, the attack trains AI agents to accept false information before stealing ...

Microsoft reverses stance and adds Google account sign-in to Edge browser

Microsoft latest release of the Edge browser adds a much-requested feature for users working within Google's web ecosystem.

macOS clipboard app Maccy has a fake out there stealing passwords

Maccy users are being warned about fake sites after researchers found malware using the app’s name to steal Mac login ...

AI browsers like Perplexity Comet can be tricked into spilling your password through BioShocking exploit

A new exploit called BioShocking convinces AI browsers they're playing a game, then gets them to hand over your private ...

Brave’s new Container feature is a lifesaver for anyone juggling multiple accounts

Brave now lets desktop users open tabs in separate Containers, so the same website can run different accounts side by side.

Smooth AI criminal drives 'first' end-to-end agentic ransomware attack

They're not bad; they're just prompted that way. Sysdig threat hunters documented what they say is the first-ever documented ...

ConsentFix and ClickFix: How Microsoft 365 Accounts are Hijacked in 3 Seconds

ConsentFix and ClickFix attacks steal Microsoft 365 tokens in seconds using fake prompts and OAuth flows. Learn how these MFA ...
SecurityWeek

‘BioShocking’ Attack Tricks AI Browsers Into Stealing Credentials

The BioShocking technique exploits AI browser reasoning, showing how easily attackers can subvert safety guardrails with ...

New BioShocking Attack Tricks AI Browsers Into Leaking Credentials

LayerX found that BioShocking could trick AI browsers into leaking credentials by disguising malicious prompts as game rules.
Bleeping Computer

ChocoPoc malware delivered via trojanized exploits on GitHub

Multiple weaponized proof-of-concept (PoC) exploits on GitHub delivered a Python-based remote access trojan (RAT) called ChocoPoC that can execute commands and steal sensitive data. However, ChocoPoC ...