AI in Cyberattacks: Anthropic's Report on Claude's Exploitation
PremiumAnthropic disclosed multiple campaigns where Claude agents automated exploitation, zero-day development, and data theft.
§Topic · AI & LLM Security
AI & LLM Security
Prompt injection, model supply chain, agent abuse, deepfakes, and the security of AI systems themselves.
All dispatchesMonday, September 14
Friday, September 11
WeChat Vulnerability Exploited by Zero-Click Worm on Mobile Devices
PremiumResearchers demonstrate a WeChat zero-click worm capable of hijacking phones via crafted calls using AI tooling.
Cybercriminals Exploit Infostealer Logs to Bypass MFA with AI Tokens
PremiumInfostealer logs reveal replayable AI tokens and API keys that attackers reuse to access model providers, bypassing MFA protections.
DeepSeek Harness Flaw Exposes AI Agents to Security Risks
PremiumDeepSeek Harness flaw allowed sandboxed AI agents to disable their file sandbox, risking arbitrary access to host files.
Exposing the Hidden Risks of AI Workflow Identity Hijacking
PremiumResearchers describe workflow identity hijacking where AI automation's privileged identities are abused to exfiltrate sensitive data.
AI-Driven Cyber Attack Compromises Hundreds of PaperCut Instances
PremiumActor used hundreds of AI agents to craft exploits for PaperCut NG/MF flaws and breached over 440 vulnerable instances.
Wednesday, September 9
ChatGPT Sandbox Flaw Exposes Gmail Data Through Hidden Channels
A ChatGPT sandbox flaw allowed covert cross-account channels to exfiltrate Gmail data from connected accounts via hidden communications.
OpenAI Unveils GPT-6 Astra: A Double-Edged Sword for Cybersecurity
OpenAI's GPT-6 Astra can find zero-days autonomously, raising detection and monitoring challenges for security teams.
Hidden ChatGPT Prompt Exploits Gmail Data to Another Account
A planted prompt in ChatGPT could cause hidden actions that read Gmail data and exfiltrate it to another ChatGPT account.
Get these articles delivered to your inbox.
Subscribe free