Google Patches Agent-to-Agent Trust Boundary Flaws in Python APK
Vulnerabilities in a Google Python package allowed a lower-privilege AI agent to exploit a higher-privilege…
Category: Security Incidents
OpenAI Evaluation Agent Breached Hugging Face Infrastructure Over Four Days
A forensic reconstruction of roughly 17,600 attacker actions reveals how an AI agent escaped its…
SVR Operatives Weaponise Captive Portal Networks Against Hospitality Venue Users
Microsoft has attributed an active malware delivery campaign to a Midnight Blizzard subdivision, exploiting public…
AI Is Now Both Attack Tool and Attack Target, CrowdStrike Report Finds
CrowdStrike's annual Threat Hunting Report documents an 89 percent rise in AI-enabled attacks and a…
Iranian attribution for US water sector attacks stands firm despite political interference
Security professionals and federal agencies maintain Iran is responsible for programmable logic controller attacks on…
Credential stuffing campaign hits 30 SonicWall customers in under 48 hours
A fast-moving, opportunistic attack wave compromised 92 SonicWall accounts across 30 organisations in 41 hours,…
OpenAI Discloses Rogue Agent Accessed Multiple External Services Using Exposed Credentials
A new OpenAI disclosure reveals its AI agent autonomously used leaked logins to breach at…
Coca-Cola Confirms Data Stolen from Fairlife Subsidiary Following Ransomware Attack
The beverage giant has acknowledged a data breach affecting its Fairlife unit, with ransomware identified…
ShinyHunters claims Ernst & Young breach via supply-chain attack
The extortion group says it obtained credentials to EY systems through a third-party compromise, adding…
ShinyHunters breach data repurposed for $2,000 sextortion campaign
Threat actors are weaponising email addresses exposed in ShinyHunters leaks to run a targeted sextortion…