Veille cybersecuritynews.com — Focus IA & Agents — 2026-11-01
Édition 2026-11-01 • 4 articles (fenêtre 7j) • ratissage large : agents autonomes, LLM, prompt injection, MCP, Copilot, red-team IA… • source : https://cybersecuritynews.com/feed/ • archives : cyberia.aq0a11q1.com/archives/
Digest brut ingéré par la synthèse Threat-Watcher du dimanche 15h (heure de Paris). La synthèse CTI reste la Une.
2026-11-01 05:24 UTC [Cyber Security, Cyber Security News, cyber security]
October brought a heavy run of cybersecurity disclosures involving cryptocurrency exchanges, web servers, AI tools, software packages, government records, and grocery chains. Binance investigated billions of dollars in unauthorized transactions, PHP issued emergency fixes, and a malicious LiteLLM release put developer credentials at risk. Other incidents involved Railway, OpenCode, Polymarket, Coinbase, Cursor, eMudhra, and Capcom. […] The post Hacktober – Cyberattack Wave Hits PHP, Node.js, Binance, LiteLLM, Pentagon, and a Few More appeared first on Cyber Security News .
2026-10-31 10:41 UTC [Cyber Security, Cyber Security News, cyber security]
Cursor has confirmed that malicious Claude Code extension packages were available through its VS Code Extension Marketplace for roughly 11 hours on October 29, 2026. The altered packages targeted Windows and macOS users and attempted to install an SSH backdoor for lasting remote access. According to Cursor’s security notice, the affected versions were Anthropic.claude-code 2.1.312 […] The post Cursor Confirms Malicious Claude Code Extension With SSH Backdoor Was Available for 11 Hours appeared first on Cyber Security News .
2026-10-31 04:48 UTC [AI, Cyber Security, Cyber Security News]
Google has announced Gemini 4 Carbon, its latest AI model built to find software flaws, test whether attackers could exploit them, and produce fixes. Unveiled on October 28, 2026, Carbon builds on Gemini 4 Argon and targets complex security and coding work that can take days. Access will begin with selected cyber defenders, not a […] The post Google Launches Gemini 4 Carbon With State-Of-The-Art Cybersecurity Capabilities appeared first on Cyber Security News .
2026-10-31 04:24 UTC [Cyber Security, Cyber Security News, cyber security]
Anthropic researchers have shown that Claude can design training data that slips past an AI safety monitor and causes a separate research model to blackmail users, weaken security code, and resist oversight. The October 2026 study exposes a gap between text that looks safe during screening and behavior learned through training. The distinction matters. These […] The post Anthropic’s Claude Bypasses AI Safety Checks, Triggering Blackmail and Code Sabotage in Tests appeared first on Cyber Security News .