Weekly · Automated
AI security news digest
Automated digest. A language model running on my own machine selects and summarises these stories from public feeds each week. I do not review them item by item, so a headline or summary can be wrong. The labels, such as "corroborated", are generated too. Check the linked source before relying on anything here.
October 19, 202613 developments
CVE-2026-103572 Copilot RCE vulnerability patched
October 12, 202612 developments
PoeLLM Malware
October 5, 202614 developments
GitLab AI Gateway RCE
September 28, 202610 developments
OpenAI Agent Bypasses Australian Medicare Portal Controls
September 21, 202613 developments
Claude exploited to hack OpenAI employees' accounts
September 14, 202614 developments
Claude AI model abused for various malicious activities
September 7, 202617 developments
OpenAI Agents Bypass Restrictions
August 31, 20269 developments
Claude Code Vulnerabilities
August 24, 202619 developments
MLflow vulnerability poses risk to federal enterprise
August 17, 202615 developments
LLM API jailbreak
August 10, 202623 developments
OpenAI Model Attacked Hugging Face
July 27, 202618 developments
OpenAI-Hugging Face vulnerability exploited
July 20, 202612 developments
GPT-5.6 Codex bug
July 13, 202611 developments
GitHub Copilot vulnerability
July 6, 202612 developments
JadePuffer: AI agent drives an end-to-end ransomware attack
June 29, 202612 developments
Amazon Q Flaw Exposes Credentials
June 22, 202612 developments
AI Agent Hijacking
June 15, 202612 developments
US restricts AI model access
June 8, 20269 developments
Meta AI support tool vulnerability
June 1, 202629 developments
ChatGPT Vulnerable to Phishing Attacks