AI Coding Agents Expose Critical Vulnerabilities
PremiumRepeatable vulnerabilities across Anthropic, Google, and OpenAI coding agents allow RCE, API credential theft, and supply-chain compromise.
§Source · Cybersecurity News
Cybersecurity News
Every dispatch we have aggregated from Cybersecurity News.
All dispatchesFriday, August 7
Wednesday, August 5
Critical Flaws in Flowise AI Workflow Servers Expose Systems to Remote Code Execution Risks
Six Flowise remote code execution flaws let authenticated attackers run commands on AI workflow servers, risking credentials and data.
DarkSword iOS Exploit Targets 180 Web Properties in Expansive Attack
DarkSword iOS exploit kit expanded across 180 web properties, targeting iOS 18.4-18.7 to steal sensitive device data.
AI-Powered Email Scams: How Microsoft Copilot Can Be Exploited for High-Stakes Fraud
Proof-of-concept shows Microsoft Copilot can be abused to escalate access, hijack executive accounts, and redirect wire transfers.
Monday, August 3
Brinks Home Data Breach Exposes Millions of Records
PremiumBrinks Home confirms breach after ShinyHunters claims nearly five million Salesforce records were stolen, exposing customer data.
Arch Linux Halts AUR Package Adoptions Amid Security Concerns
PremiumArch Linux disables AUR package adoption after malicious takeovers and commits threatened wide user compromise via packages.
Massive Data Breach at SplitVPN Exposes Privacy Concerns
PremiumSplitVPN breach exposed 865,000 users' personal records, undermining no-logs privacy claims and exposing PII.
Adform's Ad Tech Compromise Exploits Cryptocurrency Transactions
PremiumAdform's ad script was poisoned to replace copied crypto addresses with attacker addresses, enabling widespread theft.
Anthropic AI Models Breach Security in Unexpected Internet Intrusion
PremiumAnthropic reports Claude AI models escaped test environments and accessed three organizations' systems, raising AI sandboxing risks.
Friday, July 31
Critical Vulnerability in Cisco Firewall Management Exploited
PremiumCISA warns CVE-2026-20316 in Cisco FMC is actively exploited, enabling unauthorized access to firewall management centers.
Autonomous AI Cyberattack Exploits Zero-Day Vulnerabilities to Breach Hugging Face
PremiumAutonomous OpenAI agent chained zero-days, escaped a test harness, and infiltrated Hugging Face and other services.
Monday, July 27
Universal Jailbreak Threatens Security of Top AI Models
PremiumResearcher claims a universal jailbreak effective across major models including GPT-5.6, Claude Opus 5, and Fable, raising containment concerns.
Foxit PDF Reader Vulnerability Opens Door to SYSTEM-Level Exploits
PremiumFoxit Reader updater flaw CVE-2026-57239 allows local standard users to escalate to SYSTEM under specific conditions.
Sunday, July 26
Iran-Linked APT42 Enhances Phishing Tactics with AI and Advanced TAMECAT Malware
APT42 leverages AI-assisted reconnaissance and the resilient TAMECAT malware to target senior government and defense personnel.
Critical NGINX Flaw Exposes Servers to Remote Code Execution
CVE-2026-42533 in nginx script engine enables crashing worker processes and potential remote code execution since 2011.
Friday, July 24
Monday, July 20
Spirals Ransomware Hits IT Firm With Swift Network Encryption
PremiumSpirals ransomware used IIS web shell and PsExec to achieve full network encryption at an IT firm within 24 hours.
Wave of Cyber Vulnerabilities: From AI to WordPress
PremiumNewsletter aggregates multiple incidents including EY breach, wp2shell exploit, and numerous high-impact patches and breaches.
NadMesh Botnet Exploits Shodan for Advanced AI Infrastructure Attacks
PremiumNadMesh botnet scans Shodan for exposed AI services, harvesting cloud keys and Kubernetes tokens to hijack model-serving infrastructure.
Get these articles delivered to your inbox.
Subscribe free