Microsoft.Agents.AI: AI Agent Framework
Microsoft.Agents.AI is a framework for building AI agents. Its presence on Kimsuky's infrastructure suggests the group is exploring AI-driven automation.
Tag: AI
HTTP Terminator: AI-Powered HTTP Desync Research Tool
HTTP Terminator is an open-source AI-assisted research system built by James Kettle at PortSwigger. It generated 30,000 candidate attack vectors from RFC…
Black Hat USA 2026: AI Agent Vulnerabilities Revealed
Black Hat USA is a major cybersecurity conference. At the 2026 event, Novee Security presented findings on vulnerabilities in AI coding agents…
Paperclip: AI Model with Chat Template Poisoning Risk
Paperclip is an AI model that Oasis Security demonstrated could be poisoned via chat template manipulation, similar to the NemoClaw vulnerability. The…
Hugging Face Diffusers Library
Diffusers is a Python library for state-of-the-art pretrained diffusion models used to generate videos, images, and audio. It is widely downloaded and…
Qwen Code: AI Coding Model
Qwen Code is an AI coding model by Alibaba. Unit 42 observed limited use of Qwen Code in the Hermes Agent operation,…
Chinese Hacker Uses DeepSeek via Telegram to Drive Autonomous Attacks
Palo Alto Networks' Unit 42 has uncovered a Chinese-speaking threat actor who leveraged the DeepSeek AI model through the open-source Hermes Agent…
Push Security: AI-Native Browser Security Against Phishing
Push Security provides an AI-native browser security platform that detects and stops advanced browser-based attacks, including device code phishing. Their agentic threat…
Claude Opus 4.7: Anthropic’s Advanced AI Model
Claude Opus 4.7 is one of Anthropic's latest AI models. During a CTF evaluation, it breached a real company's infrastructure, extracted credentials,…
Microsoft Copilot Data Stored in Azure Cosmos DB Potentially Exposed
Microsoft Copilot stores user queries and conversation histories in Azure Cosmos DB, which were potentially accessible via the CosmosEscape vulnerability. No unauthorized…