Amazon has published a security guide for exposing AI agents via Bedrock AgentCore Runtime, emphasizing the need for robust ingress controls. The guide details how to prevent cross-tenant leakage and privilege escalation using identity propagation and layered authorization.
Cisco Talos has identified a threat actor using advanced persistence techniques, including Solana blockchain-based C2 URL updates and weaponized Windows shortcuts. The group targets financial staff, gaming users, and VoIP operators via trojanized installers and malicious LNK/HTA files.
A critical memory-corruption flaw in the OpenJDK Base64 decoder allows remote attackers to execute code. The vulnerability impacts OpenJDK 17.0.6 and newer versions on x86-64 hardware with AVX-512 support.
A high-severity vulnerability (CVE-2026-114938) has been identified in OpenJDK Java, enabling unauthenticated remote code execution. The flaw affects versions 17.0.6 and later on x86-64 hardware with AVX-512 VBMI enabled.
CISA has issued an urgent advisory regarding CVE-2026-114938, a critical memory-corruption vulnerability in the x86-64 HotSpot JVM. This flaw allows unauthenticated attackers to execute remote code via maliciously crafted Base64 input.
Microsoft has introduced 'Perception', an agentic security platform designed to manage the risks posed by AI-driven, automated cyberattacks. The platform coordinates red, blue, and green team agents through automated playbooks to detect, investigate, and remediate vulnerabilities at machine speed. This release also includes new capabilities for securing 'agentic insiders'—AI agents that act as autonomous entities within corporate networks.
Microsoft security researchers have simulated a scenario where attackers use phishing to compromise AI coding tools via OAuth device code flows. By tricking users into approving a legitimate-looking device request, attackers could gain access to private repositories, session history, and potentially control active command-line agent sessions.
The NCSC warns that standard security monitoring is no longer enough to catch sophisticated attackers, especially as adversaries adopt AI to increase the speed and scale of operations. Organizations must shift toward proactive threat hunting, focusing on enduring attacker behaviors (TTPs) rather than just changing indicators of compromise.
Siemens has patched two security vulnerabilities in the Mendix Studio Pro MCP Server. These flaws could permit remote attackers to interact with the server or execute unauthorized actions via browser-based CSRF attacks.
Researchers have introduced EndoUT, an adversarial framework that identifies universal prompt triggers capable of significantly degrading LLM utility. By analyzing how a model's internal response-onset preferences are disrupted, attackers can create fixed strings that force performance drops across various benign tasks without needing target labels or feedback.
Amazon Threat Intelligence observed autonomous agents using the open-source ARTEX framework to conduct large-scale credential theft and deepfake-based identity fraud. These campaigns exploited unpatched AI infrastructure and public misconfigurations to automate multi-stage offensive operations.
AI-powered penetration testing and orchestration frameworks have proliferated rapidly since early October, with thousands of unique instances currently active. These autonomous tools automate the entire cyber kill chain, chaining credentials to move laterally through infrastructure with unprecedented speed and scale.
Google evaluated its Agent Anomaly Detection feature using five third-party benchmarks including AgentDojo and AgentHarm. The tool successfully flagged 87% of harmful instructions that agents actually executed, though it showed lower effectiveness against poisoned long-term memory.
Microsoft researchers have demonstrated that AI coding agents can be compromised through 'dataset poisoning' and 'model poisoning'. These attacks embed dormant malicious behaviors into models, which trigger secret command-execution tool calls during benign user tasks.
Attackers are leveraging the open-source tool GSocket to maintain persistent, encrypted command-and-control access on compromised Linux servers. By utilizing a shared public relay network rather than attacker-owned infrastructure, this method bypasses traditional IP-based blocking and remains active even after initial vulnerabilities are patched.
Microsoft's FORGE Lab utilized an AI-based scanning system codenamed MDASH to analyze Linux kernel subsystems. This initiative resulted in 59 public reports and 33 assigned CVEs, revealing that AI can significantly accelerate vulnerability discovery, though human validation remains the primary bottleneck for patching.
Microsoft has released its November 2026 security updates, addressing 1095 vulnerabilities across its product ecosystem. The update includes 64 critical fixes, notably covering Azure OpenAI, Exchange Server, and Active Directory.
Microsoft Research has discovered that AI models can be compromised by modifying fewer than 10 specific neurons. These 'sleeper' backdoors allow an attacker to trigger malicious commands when specific strings appear in the context, even if the model passes all standard safety evaluations.
Microsoft researchers have uncovered 'Lazarus,' a technique that reprograms dormant neurons in LLMs to inject malicious behaviors. By modifying fewer than 10 neurons, an attacker can trigger the execution of unauthorized commands without impacting standard model performance or evaluation scores.
The Git project has released patches for six security vulnerabilities, including risks for arbitrary code execution, path traversal, and memory corruption. These flaws affect various Git operations, such as recursive cloning, merging tags, and processing binary patches.
Google DeepMind has unveiled AlphaProof Code, an agentic framework that utilizes Gemini Carbon models to perform formal verification of complex cryptographic protocols. By generating proofs in the Lean language, the system successfully verified the Signal protocol's implementation in four weeks—a task that historically required years of manual effort.
Microsoft's FORGE Lab utilized an AI-powered vulnerability scanner named Hyenas to discover critical memory safety issues within the Rust standard library. The research reveals that even safe Rust code can trigger undefined behavior when underlying 'unsafe' abstractions make false assumptions about panics or user-provided trait implementations.
Amazon has released a defense-in-depth architecture to prevent memory poisoning—a form of indirect prompt injection—in AI agents that use persistent memory. The solution uses a Lambda-based interceptor on the AgentCore Gateway to validate writes using semantic drift, regex patterns, namespace boundaries, and rate limiting.
A new report from the Linux Foundation reveals that AI-assisted coding is causing a surge in external dependencies, with 60% of organizations noting an increase. Teams are struggling to maintain this influx, as 58% report shipping code faster than security reviews can handle, leading to significant security debt.