Microsoft named a Leader in the 2026 Gartner® Magic Quadrant™ for AI Agent Management Platforms
Agents are your newest insiders. Security must move at their speed.
Managing open-weight model risk in enterprise deployments
Stay ahead of threats
Get expert insights, threat intelligence, and the latest cybersecurity reports from Security Insider.
AI and machine learning
November 12 11 min read Trained to betray: How post-training supply chain attacks hijack coding agents Microsoft Defender Research and the AI Red Team how poisoned datasets and poisoned model checkpoints can trigger remote code execution and other malicious activities.
Trained to betray: How post-training supply chain attacks hijack coding agents
November 11 7 min read Lessons from 59 Linux Kernel Bug Reports Microsoft FORGE Lab researchers used codename MDASH to investigate Linux kernel vulnerabilities, resulting in 59 upstream bug reports, 33 assigned CVEs, and 38 merged fixes.
Lessons from 59 Linux Kernel Bug Reports
November 9 16 min read FORGE Lab uses agentic tools to identify memory safety issues in Rust Microsoft FORGE Lab researchers found memory-safety bugs in Rust’s core and std libraries, including cases where safe Rust code can trigger undefined behavior.
FORGE Lab uses agentic tools to identify memory safety issues in Rust
Modernize your security operations center
Confidently secure your multicloud, multiplatform environment with Microsoft Sentinel – a cloud-native security information and event management (SIEM) solution.
November 12 11 min read Trained to betray: How post-training supply chain attacks hijack coding agents Microsoft Defender Research and the AI Red Team how poisoned datasets and poisoned model checkpoints can trigger remote code execution and other malicious activities.
Trained to betray: How post-training supply chain attacks hijack coding agents
November 11 12 min read The global socket: how threat actors are weaponizing GSocket for stealthy C2 Threat actors are deploying GSocket on compromised Linux servers to keep encrypted remote access after the original vulnerability is patched.
The global socket: how threat actors are weaponizing GSocket for stealthy C2
November 11 7 min read Lessons from 59 Linux Kernel Bug Reports Microsoft FORGE Lab researchers used codename MDASH to investigate Linux kernel vulnerabilities, resulting in 59 upstream bug reports, 33 assigned CVEs, and 38 merged fixes.
Lessons from 59 Linux Kernel Bug Reports
November 10 5 min read Detecting sleeper agents hiding in AI model neurons Microsoft Research has released new threat research detailing how a capable agent model could be turned into a sleeper agent by editing fewer than ten neurons to inject a short payload; Microsoft Research has also found that this threat is detectable by frontier agents, which can identify anomalous weight edits.
Detecting sleeper agents hiding in AI model neurons
November 9 16 min read FORGE Lab uses agentic tools to identify memory safety issues in Rust Microsoft FORGE Lab researchers found memory-safety bugs in Rust’s core and std libraries, including cases where safe Rust code can trigger undefined behavior.
FORGE Lab uses agentic tools to identify memory safety issues in Rust
November 6 8 min read ARTEX abuse expands as cybercriminals target financial sector In October 2026, the financially motivated threat actor Storm-3358 began targeting organizations in the financial sector using the agentic AI offensive framework ARTEX.
ARTEX abuse expands as cybercriminals target financial sector
The full story
This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.
