Skip to content
Thursday, 19 November 2026
Tenesys AI News
Subscribe

All News

TENESYS AI NEWS tracks the most important AI news and explains what changed, why it matters and whether a technology is worth testing.

“Security” — 91 articles ✕

BreakingCyber Security· 🧪 Worth Testing

Microsoft Launches Perception to Automate Security for Agentic AI Environments

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
Agents· Important· 🧪 Worth Testing

Microsoft and Salesforce integrate AI agents via Copilotforce

Microsoft and Salesforce have launched Copilotforce, an initiative that integrates Salesforce customer data and workflows into Microsoft Copilot and Teams. The partnership uses authenticated MCP access to allow AI agents to act on CRM data while respecting existing security and permissions.

Microsoft
Agents· Important· 🧪 Worth Testing

A Phased Framework for Scaling Agentic AI Safely

Amazon has published a three-phase roadmap to help platform and application teams operationalize Responsible AI for agentic systems. It addresses the challenges of nondeterministic behavior, data boundary isolation, and regulatory compliance as agents move from pilot to production.

AWS Machine Learning
Cyber Security· Important· 🧪 Worth Testing

Why threat hunting is essential for modern cyber defense

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.

NCSC UK
Cyber Security· Important· 🧪 Worth Testing

New Adversarial Research Reveals Universal Vulnerabilities in LLM Utility

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.

arXiv cs.CL
Agents· Important· 🧪 Worth Testing

Amazon Bedrock introduces automated memory for agentic applications

Amazon Bedrock has launched a new memory-aware capability for AgenticRetrieveStream. This feature automates the storage, extraction, and retrieval of user-specific facts and conversation histories, allowing agents to provide context-aware responses while maintaining strict document-level access control.

AWS Machine Learning
Agents· Important· 🧪 Worth Testing

Scaling agentic platforms using MCP and Amazon Bedrock AgentCore

MoEngage has integrated AI agents into its customer engagement platform by using the Model Context Protocol (MCP) and Amazon Bedrock AgentCore to expose existing APIs as agent-callable tools. By treating its platform as an architecture of isolated sessions and standardized tool schemas, the company enabled teams to automate workflows and decision-making within a single conversation.

AWS Machine Learning
Research· Important· 🧪 Worth Testing

LLM Behavior Control via Input Optimization

Researchers introduced ActGCG, a method to replicate the effects of activation steering—typically requiring internal model access—by optimizing input suffixes. The technique successfully reproduces specific behaviors like language steering through external text inputs alone.

arXiv cs.CL
Models· Important· 🧪 Worth Testing

Optimizing coding agent costs on Amazon Bedrock with NVIDIA NeMo Switchyard

Amazon has released a reference architecture that integrates the NVIDIA NeMo Switchyard library with LiteLLM to dynamically route coding agent requests between different models on Bedrock. By using stage or random routing, you can shift traffic between high-capability and high-efficiency models to balance performance and cost.

AWS Machine Learning
Cyber Security· Important· 🧪 Worth Testing

Threat actors using ARTEX AI agent framework for large-scale cybercrime

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.

AWS Security
BreakingCyber Security· 🧪 Worth Testing

Rise of Autonomous AI Penetration Testing Frameworks

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.

Cloudflare Security
Models· Important· 🧪 Worth Testing

IBM releases LLMON-enabled Granite models to combat prompt injection

IBM has introduced LLMON (LLM Object Notation), an XML-like markup language that uses reserved special tokens to explicitly label components like instructions, data, and constraints. Two experimental models, Granite 4.1 3B and 8B LLMON-preview, are now available, demonstrating near-zero success rates for indirect prompt injection attacks.

Hugging Face
Cyber Security· Important· 🧪 Worth Testing

New research exposes supply chain vulnerabilities in AI coding agents

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.

Microsoft Security
Agents· Important· 🧪 Worth Testing

AWS Updates Bedrock AgentCore Runtime for Faster, More Efficient AI Agents

Amazon has released a next-generation runtime for Bedrock AgentCore designed to handle complex, long-running AI agent workloads. The update brings hardware-isolated environments with faster startup times, increased compute capacity, and improved cost efficiency through usage-based billing.

AWS Machine Learning
BreakingAgents· 🧪 Worth Testing

Anthropic introduces self-hosted Claude Managed Agents

Organizations can now deploy the entire Managed Agents service, including agents and session history, on their own infrastructure. Model requests remain flexible, with the ability to route traffic to chosen providers.

Claude Platform Release Notes
Agents· Important· 🧪 Worth Testing

Standardized Cross-Organization Agent Communication with A2A

AWS is now supporting the Linux Foundation's A2A protocol, designed to enable secure collaboration between agents across different organizational boundaries. This approach allows agents built on disparate frameworks (such as LangChain and Strands Agents) to exchange tasks and data as peers without exposing internal logic or sharing secrets.

AWS Machine Learning
Agents· Important· 🧪 Worth Testing

Implementing Secure Fine-Grained Access Control in Amazon Bedrock Managed Knowledge Bases

Amazon introduced a pattern for securing multi-tenant AI agents by ensuring that RAG search queries are scoped to specific users. The solution uses ACL-aware knowledge bases combined with a request interceptor in the AgentCore Gateway to deterministically inject verified user identities into tool calls, preventing LLMs or prompt injections from accessing unauthorized data.

AWS Machine Learning
Models· Important· 🧪 Worth Testing

Direct Web Search Access Added to Amazon Bedrock AgentCore

Amazon now offers a direct Web Search API for Bedrock AgentCore, enabling developers to perform web searches via standard AWS SDKs and CLI. This bypasses the need for the AgentCore Gateway, simplifying the process for custom agent loops and non-agent applications that require real-time information.

AWS Machine Learning
Automation· Important· 🧪 Worth Testing

NVIDIA AICR Now Includes AI Bill of Materials for Workload Tracking

NVIDIA has integrated the open-source k8s-aibom project into its AI Cluster Runtime (AICR). This allows platform teams to automatically generate and audit an AI Bill of Materials (AIBOM) for workloads running on Kubernetes, identifying models, inference runtimes, and dependencies.

NVIDIA Developer
Cyber Security· Important· 🧪 Worth Testing

Microsoft researchers use AI agents to find 59 Linux kernel vulnerabilities

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 Security
Models· Important· 🧪 Worth Testing

Tether AI Research releases BotPsy: A high-performance 0.8B agentic model

Tether AI Research has introduced BotPsy, a 0.8B-parameter language model optimized for agentic workflows and function calling. Built on Qwen3.5-0.8B, the model is designed for on-device deployment, offering superior tool-use reliability and instruction following while maintaining data privacy.

Hugging Face
Cyber Security· Important· 🧪 Worth Testing

New research shows how AI models can be turned into sleeper agents

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 Security
Cyber Security· Important· 🧪 Worth Testing

New Lazarus backdoor technique targets dormant AI model neurons

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.

Microsoft Research