Updating the taxonomy of failure modes in agentic AI systems: What a year of red teaming taught us

In this article 1. Why the Taxonomy Needed Updating 2. Seven new failure modes 3. Operational findings: What red teaming showed 4. New mitigations 5. What to do this quarter When the Microsoft AI Red Team published the Taxonomy of Failure Modes in Agentic AI Systems in April 2025, the goal was a...

Reporting from Vegas: Networking, AI, and good boys

Welcome to this week's edition of the Threat Source newsletter. Howdy friends, and hello from Cisco Live U.S., here in sunny and very hot Las Vegas! An interesting quirk of being sent to one of these events is you learn to understand your limits as a person. Cisco Live is a three-day event, and i...

Agentic AI Is Transforming Defense, But Only Secure IT Infrastructure Will Maximize It

Over the past several weeks, the cybersecurity community has been reminded how quickly frontier and agentic AI in defense networks can challenge our assumptions. When Anthropic's Claude Mythos model was made available to a limited set of organizations as a technical preview, it was reported that ...

AI Threat Readiness Pillar 1: Reduce Critical Exposures & Scan with AI

Diving into the first pillar of the AI Threat Readiness Framework and how Wiz helps...

Hypotheses, telemetry, and human judgment: Inside Cisco Talos Threat Hunting

By Ron Scott-Adams Most security tools operate on a simple principle: If a known-bad pattern appears, fire an alert. This works well enough for many threats, but it fails against adversaries who closely study detection thresholds and deliberately stay under them. Cisco Talos Threat Hunting operat...

Hacking Meta’s AI Chatbot

Hackers are convincing Meta's AI support chatbot to let them take over other peoples' accounts: A video posted on X showed the step-by-step process to hack someone's Instagram account. The hacker allegedly used a VPN to spoof the targets' presumed location to avoid triggering Instagram's automate...

Hackers Spied on a Stock Exchange Executive's Outlook Mailbox for Five Months

Unknown attackers spent at least five months inside the Outlook mailbox of a senior executive at a major global stock exchange, copying the inbox out in small, repeated batches and routing it through Dropbox and OneDrive so the traffic blended into normal cloud activity. Symantec and Carbon Black...

Meta’s AI support bot happily handed Instagram accounts to hackers

Customer service chatbots have one job: get the user what they're asking for without bothering a human. Meta's new AI support assistant took that brief a little too seriously. Over the past few months, attackers have been opening support chats, telling the bot they were locked out of Instagram...

CVE-2025-65640

Cross Site Scripting XSS vulnerability in the "Task in Progress / Recent" page in Arket Globe Document Intelligence 5.0.0.559 due to improper sanitization of user input in text fields when creating a new document. Specifically, when an authenticated attacker submits data containing JavaScript cod...

Explainable AI-Driven Cyber Risk Analytics and Model Reliability Assessment for Intelligent Governance of U.S. Critical Infrastructure: An XGBoost and SHAP-Based Intrusion Detection Framework

The increasing penetrations of the critical infrastructure sector in the United States with intelligent digital technologies have greatly increased exposure to advanced cyber adversaries and operational vulnerabilities. AI-powered governance and automated decision-making systems are becoming a ke...

Arket Globe Document Intelligence 跨站脚本漏洞

Arket Globe Document Intelligence is an enterprise document intelligence management platform developed by the Italian company Arket. Version 5.0.0.559 of Arket Globe Document Intelligence contains a security vulnerability. This vulnerability arises from improper handling of user input in text...

Cognitive Threat Intelligence and Explainable Federated Security Analytics for Distributed Infrastructure Systems

The increasing adoption of distributed infrastructure systems, cloud computing, Internet of Things IoT technologies, and edge-based architectures has significantly expanded the cybersecurity attack surface and introduced increasingly sophisticated cyber threats. Conventional centralized intrusion...

GenTI: Benchmarking LLMs for Autonomous IDPS Rule Generation for Unseen Attacks

Rule-based Intrusion Detection and Prevention Systems IDPS offer precise attack detection as well as mitigation, however their manually crafted, signature-driven rules limit adaptability to emerging and zero-day threats. Additionally, existing public datasets e.g., CICIDS2017, UNSW-NB15 focus on...

CVE-2025-65640

Cross Site Scripting XSS vulnerability in the "Task in Progress / Recent" page in Arket Globe Document Intelligence 5.0.0.559 due to improper sanitization of user input in text fields when creating a new document. Specifically, when an authenticated attacker submits data containing JavaScript cod...

CVE-2025-65640

The CVE-2025-65640 issue affects Arket Globe Document Intelligence 5.0.0.559 (Task in Progress / Recent page). It is a Cross Site Scripting (XSS) vulnerability caused by improper sanitization/escaping of user input in text fields when creating a new document, allowing injected JavaScript to run i...

ExploitGym AI Exploit Benchmark Tool

ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits...

Important: Red Hat Security Advisory: satellite/foreman-mcp-server-rhel9 container image available as a Technology Preview

A new satellite/foreman-mcp-server-rhel9 container image is now available as a Technology Preview in the Red Hat container registry. Satellite provides a container image that you can use to run an MCP server locally. The MCP server for Satellite is designed for advanced reporting and data analysi...

xAI Asks Court to Strip Alleged Grok Deepfake Nudes Victims of Anonymity

Four people suing Elon Musk's AI firm under pseudonyms due to the risks of being identified may face a difficult choice: Reveal your real names, or drop the lawsuit...

Optimize AI Inference: Real-Time NodeBalancers Metrics for AI Workloads

...

Shrinking the IAM Attack Surface through Identity Visibility and Intelligence Platforms (IVIP)

The Fragmented State of Modern Enterprise Identity Enterprise IAM is approaching a breaking point. As organizations scale, identity becomes increasingly fragmented across thousands of applications, decentralized teams, machine identities, and autonomous systems. The result is Identity Dark Matter...