Tag: Microsoft Security Blog

Guarding AI memory

What happens when threat actors target what AI remembers? Microsoft breaks down the risks and the defenses. The post Guarding AI memory appeared first on Microsoft Security Blog. This article has been indexed from Microsoft Security Blog Read the original…

Crypto Clipper uses Tor and worm-like propagation for persistence and control

Microsoft Threat Intelligence analyzed a cryptocurrency clipper campaign that combines clipboard theft, wallet replacement, Tor-based communications, and worm-like propagation. Beyond stealing cryptocurrency transactions, the malware establishes persistent access and enables follow-on activity through a lightweight backdoor capability. The post Crypto…

Beyond the benchmark: Advancing security at AI speed

Read how Microsoft Security has advanced its agentic vulnerability detection system, codename MDASH, integrating into real-world workflows across Windows, Azure, and identity systems. The post Beyond the benchmark: Advancing security at AI speed  appeared first on Microsoft Security Blog. This…

AI is accelerating cyberattacks—here’s how to stay ahead

See how Microsoft unifies identity and security signals to help teams prevent, detect, and respond to AI-accelerated attacks faster. The post AI is accelerating cyberattacks—here’s how to stay ahead appeared first on Microsoft Security Blog. This article has been indexed…

Turn specs into evals for any agent with ASSERT

Adaptive Spec-driven Scoring for Evaluation and Regression Testing (ASSERT) is an open-source framework for converting natural language behavior requirements into executable evaluations of AI models and agents. The post Turn specs into evals for any agent with ASSERT appeared first…

Reconstructing AI activity in investigations

Learn how to investigate AI activity in Microsoft 365 Copilot and Azure AI services using a structured, telemetry-driven approach. This playbook helps security teams reconstruct events, assess data exposure, and detect potential threats faster. The post Reconstructing AI activity in…

Securing CI/CD in an agentic world: Claude Code Github action case

Microsoft Threat Intelligence identified a prompt injection pathway in Claude Code GitHub Action that allowed access to workflow secrets under specific conditions. This research examines the attack chain, responsible disclosure process, Anthropic’s mitigation, and guidance for securing AI-powered CI/CD workflows.…

Typosquatted npm packages used to steal cloud and CI/CD secrets

The Mini Shai-Hulud campaign used malicious npm packages to target cloud and CI/CD credentials across developer environments. This report details the attack chain, detection opportunities, and mitigation guidance to help organizations identify and disrupt related activity. The post Typosquatted npm…