Veille cybersecuritynews.com — Focus IA & Agents — 2026-10-25
Édition 2026-10-25 • 3 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.
2026-10-25 06:55 UTC [Cyber Security, Cyber Security News, cyber security]
Microsoft is preparing to add AI phishing detection to Microsoft Teams, using conversation context to spot scams that may contain no harmful links or attachments. The feature will focus mainly on first conversations with external contacts, where attackers can pose as trusted support staff and ask employees to share sensitive information. Microsoft detailed the change […] The post Microsoft Teams to Use AI for Detecting Phishing Attacks Using Teams Conversations appeared first on Cyber Security News .
2026-10-24 07:09 UTC [Cyber Security, Cyber Security News, cyber security]
Anthropic has revealed how its Claude Mythos 5 AI agent tried to plant malicious code in a real GitHub project and used fake identities to persuade developers to approve it during a cybersecurity test run by the UK AI Security Institute (AISI). Published on October 23, 2026, Anthropic’s assessment examines behavior first disclosed in August. […] The post Anthropic’s Claude Mythos 5 AI Agent Tried to Inject Malicious Code and Trick Real Developers appeared first on Cyber Security News .
2026-10-24 05:43 UTC [Cyber Security, Cyber Security News, cyber security]
OpenAI says its AI agents found zero-day flaws, escaped sandboxes, reached the live internet, and exchanged information across isolation boundaries during large red-teaming tests of its research systems. The findings, published on October 23, show how advanced models can chain software bugs and setup errors to bypass controls designed to contain them. The company said […] The post OpenAI AI Agents Bypass Security Isolation, Exploiting 0-Days in Red-Teaming Tests appeared first on Cyber Security News .