-
Chinese government-backed hackers used Anthropic’s Claude Code tool to carry out advanced spying on about thirty targets worldwide, successfully breaking into several major organizations. The first documented large-scale cyberattack executed primarily by leveraging artificial intelligence with minimal human intervention. The operation, detected in mid-September 2025 by Anthropic security team, targeted leading tech companies, financial institutions, […] The post First Large-scale Cyberattack Using AI Tools With Minimal Human Input appeared first on Cyber Security News.
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
A vulnerability in OpenAI’s advanced video generation model, Sora 2, that enables the extraction of its hidden system prompt through audio transcripts, raising concerns about the security of multimodal AI systems. This vulnerability, detailed in a blog post by AI security firm Mindgard, demonstrates how creative prompting across text, images, video, and audio can bypass […] The post OpenAI Sora 2 Vulnerability Exposes System Prompts via Audio Transcripts appeared first on Cyber Security News.
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
BruteForceAI, an innovative penetration testing framework developed by Mor David, integrates large language models (LLMs) with browser automation to autonomously identify login forms and conduct sophisticated brute-force attacks. By combining AI-driven form analysis with evasion techniques and comprehensive logging, BruteForceAI streamlines credential-testing workflows, enabling security teams to uncover weak authentication mechanisms rapidly and efficiently. At […] The post New BruteForceAI Tool Automatically Detects Login Pages and Executes Smart Brute-Force Attacks appeared first on Cyber Security News.
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Hackers can weaponize hidden prompts revealed by downscaled images to trigger sensitive tool actions and achieve data exfiltration in Gemini CLI—and similar risks extend to Google Assistant and other production AI systems, according to new research by Trail of Bits. By exploiting how AI services routinely apply image scaling, the researchers showed that a benign-looking upload can morph […] The post Hackers Can Exploit Image Scaling in Gemini CLI, Google Assistant to Exfiltrate Sensitive Data appeared first on Cyber Security News.
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
By now, you’ve heard the hype. Agentic AI; self-directed and goal-oriented. Supposedly, the next big thing in security automation. If you’re working in a Security Operations Center (SOC), it might sound like déjà vu. Agentic AI brings autonomous, deci…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
