Security & IT News

The Trump administration has deployed ICE agents to over a dozen U.S. airports amid an ongoing federal shutdown that's causing long wait times. Eyewitnesses have already recorded at least one arrest in San Francisco's airport.

It’s an impressive feat , over a decade after the box was released: Since reset glitching wasn’t possible, Gaasedelen thought some voltage glitching could do the trick. So, instead of tinkering with the system rest pin(s) the hacker targeted the momentary collapse of the CPU voltage rail. This was quite a feat, as Gaasedelen couldn’t ‘see’ into the Xbox One, so had to develop new hardware introspection tools. Eventually, the Bliss exploit was formulated, where two precise voltage glitches were made to land in succession. One skipped the loop where the ARM Cortex memory protection was setup. Then the Memcpy operation was targeted during the header read, allowing him to jump to the attacker-controlled data. As a hardware attack against the boot ROM in silicon, Gaasedelen says the attack in unpatchable. Thus it is a complete compromise of the console allowing for loading unsigned code at every level, including the Hypervisor and OS. Moreover, Bliss allows access to the security processor so games, firmware, and so on can be decrypted.

(c) SANS Internet Storm Center. https://isc.sans.edu Creative Commons Attribution-Noncommercial 3.0 United States License.

An anonymous Substack post accuses compliance startup Delve of “falsely” convincing “hundreds of customers they were compliant” with privacy and security regulations.

The population needs better conservation. As usual, you can also use this squid post to talk about the security stories in the news that I haven’t covered. Blog moderation policy.

♫ I Just Called ♫ To Say ♫ 7f45 4c46 0201 0100 0000 0000 0000 0000 0300 3e00 0100♫ This release contains 2 new exploit modules, 2 enhancements, and 7 bug fixes. Community contributor Chocapikk submitted both exploit modules this release: one targeting AVideo-Encoder’s getImage.php file and another targeting FreePBX. Leading the enhancements is a granularization for LDAP queries allowing the omission of SACL data on security descriptors, as without the proper permissions the entire query of the security descriptor will fail if the SACL data is even just a part of the query. New module content (2) AVideo Encoder getImage.php Unauthenticated Command Injection Authors: Valentin Lobstein [email protected] and arkmarta Type: Exploit Pull request: #21076 contributed by Chocapikk Path: linux/http/avideo_encoder_getimage_cmd_injection AttackerKB reference: CVE-2026-29058 Description: Adds an exploit module for CVE-2026-29058, an unauthenticated OS command injection in AVideo Encoder's getImage.php endpoint. FreePBX filestore authenticated command injection Authors: Cory Billington and Valentin Lobstein [email protected] Type: Exploit Pull request: #20719 contributed by Chocapikk Path: unix/http/freepbx_filestore_cmd_injection AttackerKB reference: CVE-2025-64328 Description: Adds a new Metasploit exploit module for FreePBX filestore authenticated command injection (CVE-2025-64328) with automatic vulnerable-version detection and full documentation, and renames the XorcomCompletePbx HTTP mixin to CompletePBX updating affected modules accordingly. Enhancements and features (2) #20730 from zeroSteiner - This update modifies the ldap_query module to skip querying the SACL (System Access Control List) on security descriptors by default. This behavior is now controlled by a new option, LDAP::QuerySacl. This change is necessary when using a non-privileged user to query security descriptors via LDAP; otherwise, querying the SACL will cause the entire query to be blocked, resulting in no security descriptors being returned. #20997 from Nayeraneru - This adds a new OptTimedelta datastore option type. It enables module authors to specify a time duration and users to set it with a human-friendly syntax. Bugs fixed (7) #20960 from g0tmi1k - This adds a DHCPINTERFACE option to the DHCP server mixin, allowing modules that start that server to specify a particular interface to bind to. #21020 from g0tmi1k - This makes a small change to the docs by removing two lines that were previously duplicated. #21024 from Aaditya1273 - Fixes a bug in the JSON-RPC msfrpcd functionality that incorrectly required SSL certificates to be present even when disabled with msfrpcd -S. #21025 from Hemang360 - Fixes a crash when calling the HTTP cookie jar with non-string values. #21028 from SilentSobs - Fixes a crash when using the reload_all command no module is present. #21081 from Hemang360 - Fixes a crash when using the windows/exec with non-ascii characters. #21139 from jheysel-r7 -

A French naval officer went on a run around the deck of the Charles de Gaulle aircraft carrier, inadvertently leaking the warship's location when he uploaded the workout to Strava.

Excerpt: CTI-REALM is Microsoft’s open-source benchmark for evaluating AI agents on real-world detection engineering—turning cyber threat intelligence (CTI) into validated detections. Instead of measuring “CTI trivia,” CTI-REALM tests end-to-end workflows: reading threat reports, exploring telemetry, iterating on KQL queries, and producing Sigma rules and KQL-based detection logic that can be scored against ground truth across Linux, AKS, and Azure cloud environments. Security is Microsoft’s top priority. Every day, we process more than 100 trillion security signals across endpoints, cloud infrastructure, identity, and global threat intelligence. That’s the scale modern cyber defense demands, and AI is a core part of how we protect Microsoft and our customers worldwide. At the same time, security is, and always will be, a team sport. That’s why Microsoft is committed to AI model diversity and to helping defenders apply the latest AI responsibly. We created CTI‑REALM and open‑sourced it so the broader industry can test models, write better code, and build more secure systems together. CTI-REALM (Cyber Threat Real World Evaluation and LLM Benchmarking) is Microsoft’s open-source benchmark that evaluates AI agents on end-to-end detection engineering. Building on work like ExCyTIn-Bench , which evaluates agents on threat investigation, CTI-REALM extends the scope to the next stage of the security workflow: detection rule generation. Rather than testing whether a model can answer CTI trivia or classify techniques in isolation, CTI-REALM places agents in a realistic, tool-rich environment and asks them to do what security analysts do every day: read a threat intelligence report, explore telemetry, write and refine KQL queries, and produce validated detection rules. We curated 37 CTI reports from public sources (Microsoft Security, Datadog Security Labs, Palo Alto Networks, and Splunk), selecting those that could be faithfully simulated in a sandboxed environment and that produced telemetry suitable for detection rule development. The benchmark spans three platforms: Linux endpoints, Azure Kubernetes Service (AKS), and Azure cloud infrastructure with ground-truth scoring at every stage of the analytical workflow. Why CTI-REALM exists Existing cybersecurity benchmarks primarily test parametric knowledge: can a model name the MITRE technique behind a log entry, or classify a TTP from a report? These are useful signals. However, they miss the harder question: can an agent operationalize that knowledge into detection logic that finds attacks in production telemetry? No current benchmark evaluates this complete workflow. CTI-REALM fills that gap by measuring: Operationalization, not recall: Agents must translate narrative threat intelligence into working Sigma rules and KQL queries, validated against real attack telemetry. The full workflow: Scoring captures intermediate decision quality—CTI report selection, MITRE technique mapping, data source identi

The U.S. Justice Department said an Iranian security ministry operates the fake activist persona known as Handala, which claimed responsibility for the destructive hack targeting medical tech giant Stryker.

Next week, RSAC™ Conference celebrates its 35-year anniversary as a forum that brings the security community together to address new challenges and embrace opportunities in our quest to make the world a safer place for all. As we look towards that milestone, agentic AI is reshaping industries rapidly as customers transform to become Frontier Firms —those anchored in intelligence and trust and using agents to elevate human ambition, holistically reimagining their business to achieve their highest aspirations. Our recent research shows that 80% of Fortune 500 companies are already using agents. 1 At the same time, this innovation is happening against a sea change in AI-powered attacks where agents can become “ double agents .” And chief information officers (CIOs), chief information security officers (CISOs), and security decision makers are grappling with the resulting security implications: How do they observe, govern, and secure agents? How do they secure their foundations in this new era? How can they use agentic AI to protect their organization and detect and respond to traditional and emerging threats? The answer starts with trust, and security has always been the root of trust. In this agentic era, security must be woven into, and around, every layer of the AI estate. It must be ambient and autonomous, just like the AI it protects. This is our vision for security as the core primitive of the AI stack. At RSAC 2026, we are delivering on that vision with new purpose-built capabilities designed to help organizations secure agents, secure their foundations, and defend using agents and experts. Fueled by more than 100 trillion daily signals, Microsoft Security helps protect 1.6 million customers, one billion identities, and 24 billion Copilot interactions. 2 Read on to learn how we can help you secure agentic AI. Secure agentic AI with Microsoft Security Secure agents Earlier this month, we announced that Agent 365 will be generally available on May 1. Agent 365—the control plane for agents —gives IT, security, and business teams the visibility and tools they need to observe, secure, and govern agents at scale using the infrastructure you already have and trust. It includes new Microsoft Defender, Entra, and Purview capabilities to help you secure agent access, prevent data oversharing, and defend against emerging threats. Agent 365 is included in Microsoft 365 E7: The Frontier Suite along with Microsoft 365 Copilot, Microsoft Entra Suite, and Microsoft 365 E5, which includes many of the advanced Microsoft Security capabilities below to deliver comprehensive protection for your organization. Learn more about Microsoft Agent 365 Secure your foundations Along with securing agents, we also need to think of securing AI comprehensively. To truly secure agentic AI, we must secure foundations—the systems that agentic AI is built and runs on and the people who are developing and using AI. At RSAC 2026, we are introducing new capabilities to help you gain

Security leaders rarely struggle to produce data. The challenge is turning that data into something the board can use to make decisions. Walk into a board meeting with a slide showing 1,200 critical vulnerabilities and 44 internet-facing assets, and you will likely see polite acknowledgment rather than meaningful discussion. The question that follows tends to cut through quickly: what does this mean for the business? Boards allocate capital based on financial exposure, not vulnerability counts. A list of findings describes workload, but directors are responsible for revenue protection, liability, and risk to the balance sheet. When security reporting remains technical, it sits outside the way investment decisions are made elsewhere in the organization. The issue is less about communication and more about framing the problem in terms the business already understands. From severity to risk CVSS measures theoretical severity, but it does not measure business risk. A high score indicates that a flaw could be dangerous, yet it does not tell you whether the vulnerability is reachable in your environment, whether exploit code exists, or whether it is likely to affect revenue in the near term. It answers a useful engineering question, but it does not answer the question the board is asking. That question is about likelihood and impact. Most enterprise risk frameworks define risk in those terms, and that is how financial decisions are made. The gap becomes clear when two vulnerabilities appear similar on a dashboard but carry very different consequences. A high-CVSS issue on a segmented lab system may present little business risk, while a moderately severe vulnerability on an internet-facing production system with active exploit activity can expose regulated data and revenue streams. What is often missing in that comparison is threat context. Understanding how attackers behave, which vulnerabilities they are exploiting, and where access paths actually exist changes how risk is interpreted. Active Risk in InsightVM brings those elements together by combining exploit telemetry, attacker behavior, and asset context to estimate the likelihood that a vulnerability will be used. When that likelihood is paired with business impact, the conversation shifts toward exposure rather than severity. From CVSS scores to financial exposure Prioritization alone does not translate into board-level decisions. Knowing what is most likely to be exploited is necessary, but it is not sufficient when the goal is to justify investment. FAIR provides a way to bridge that gap. The model defines risk as a combination of how often a loss event is likely to occur and how much that event would cost. In practical terms: Annualized Loss Exposure (ALE) = Loss Event Frequency × Probable Loss Magnitude Active Risk informs the likelihood side of that equation by grounding it in observed attacker behavior and exploit activity. FAIR converts that likelihood into financial terms, allowing secur

Overview Rapid7 Labs recently identified a chain of security vulnerabilities in the Gainsight Assist plugin and its interactions with the associated domain app.gainsight.com . These vulnerabilities include an Information Disclosure flaw ( CVE-2026-31381 ) and a Reflected Cross-Site Scripting (XSS) vulnerability ( CVE-2026-31382 ). By chaining these vulnerabilities, an attacker can move from passive information gathering to active client-side exploitation. The XSS vulnerability was remediated by Gainsight via a server side code-level fix on March 6, 2026. A patched update to the Chrome and Outlook plugins to remediate the Information Disclosure were released on March 9, 2026. Product description Gainsight Assist is a plugin that allows users to access Gainsight email templates and easily sync inbound and outbound emails to the Timeline within the Gainsight Customer Success (CS) product directly from their email platform. Credit These vulnerabilities were discovered and reported to the Gainsight team by Christopher O’Boyle, Cybersecurity Advisor at Rapid7. The vulnerabilities are being disclosed in accordance with Rapid7's vulnerability disclosure policy . Rapid7 is grateful to the Gainsight team for their assistance and collaboration. Vulnerability details CVE Description CVSS CVE-2026-31381 Information Disclosure: An attacker can extract user email addresses (PII) exposed in base64 encoding via the state parameter in the OAuth callback URL. 5.3 (Medium) CVE-2026-31382 Reflected XSS / HTML Injection: The error_description parameter is vulnerable to Reflected XSS. An attacker can bypass the domain's WAF using a Safari-specific onpagereveal payload. 6.1 (Medium) The testing target was the Gainsight Assist plugin and its interactions with the app.gainsight.com domain, used as a callback mechanism that processes authentication data and error descriptions following user login attempts. CVE-2026-31381: Information disclosure During testing involving Salesforce and Okta authentication channels, an OAuth callback flow failure was observed. The resulting error message exposed the user's email address (PII) within a Base64 encoded state parameter in the URL. Because Base64 is merely obfuscation and not encryption, these email addresses can be easily harvested from server logs, proxies, or browser history by third parties. CVE-2026-31382: Reflected XSS and HTML injection The Gainsight callback URL contained an error_description parameter that was found to be vulnerable to content spoofing and HTML Injection. While Gainsight employs a Web Application Firewall (WAF) that successfully blocks most standard JavaScript execution, Rapid7 researchers bypassed this protection using a browser-specific payload targeting Safari’s onpagereveal event. When the victim opens the malicious URL in Safari, the onpagereveal payload executes automatically without further user interaction. By injecting HTML content and spoofing the error page, an attacker can create a legitimate-

p CISA and the Federal Bureau of Investigation released a a href= https://www.ic3.gov/PSA/2026/PSA260320 target= _blank Public Service Announcement (PSA) /a warning about ongoing phishing campaigns by cyber actors associated with the Russian Intelligence Services targeting commercial messaging applications (CMAs). These campaigns aim to bypass encryption to compromise to individual user accounts with targets including current and former U.S. government officials, military personnel, political figures, and journalists. nbsp; nbsp; /p p Evidence shows that cyber actors have been able to compromise individual CMA accounts, but not encryption of the applications themselves. The actors’ global campaigns have resulted in unauthorized access to thousands of individual CMA accounts to view the victims’ messages and contact lists, send messages, and conduct additional phishing against other CMA accounts. nbsp; /p p CISA and FBI urge CMA users to review the PSA, follow recommended cybersecurity practices, and remain vigilant for suspicious activity. /p

p CISA has added five new vulnerabilities to its a href="https://www.cisa.gov/known-exploited-vulnerabilities-catalog" data-entity-type="node" data-entity-uuid="79453b83-86b9-4e2f-b1ec-abf73c6eb291" data-entity-substitution="canonical" title="Known Exploited Vulnerabilities Catalog" Known Exploited Vulnerabilities (KEV) Catalog /a , based on evidence of active exploitation. /p ul li a href="https://www.cve.org/CVERecord?id=CVE-2025-31277" target="_blank" CVE-2025-31277 /a Apple Multiple Products Buffer Overflow Vulnerability /li li a href="https://www.cve.org/CVERecord?id=CVE-2025-32432" target="_blank" CVE-2025-32432 /a Craft CMS Code Injection Vulnerability /li li a href="https://www.cve.org/CVERecord?id=CVE-2025-43510" target="_blank" CVE-2025-43510 /a Apple Multiple Products Improper Locking Vulnerability /li li a href="https://www.cve.org/CVERecord?id=CVE-2025-43520" target="_blank" CVE-2025-43520 /a Apple Multiple Products Classic Buffer Overflow Vulnerability /li li a href="https://www.cve.org/CVERecord?id=CVE-2025-54068" target="_blank" CVE-2025-54068 /a Laravel Livewire Code Injection Vulnerability /li /ul p These types of vulnerabilities are frequent attack vectors for malicious cyber actors and pose significant risks to the federal enterprise. /p p a href="https://www.cisa.gov/binding-operational-directive-22-01" Binding Operational Directive (BOD) 22-01: Reducing the Significant Risk of Known Exploited Vulnerabilities /a established the KEV Catalog as a living list of known Common Vulnerabilities and Exposures (CVEs) that carry significant risk to the federal enterprise. BOD 22-01 requires Federal Civilian Executive Branch (FCEB) agencies to remediate identified vulnerabilities by the due date to protect FCEB networks against active threats. See the a href="https://www.cisa.gov/sites/default/files/publications/Reducing_the_Significant_Risk_of_Known_Exploited_Vulnerabilities_211103.pdf" BOD 22-01 Fact Sheet /a for more information. /p p Although BOD 22-01 only applies to FCEB agencies, CISA strongly urges all organizations to reduce their exposure to cyberattacks by prioritizing timely remediation of a href="https://www.cisa.gov/known-exploited-vulnerabilities-catalog" data-entity-type="node" data-entity-uuid="79453b83-86b9-4e2f-b1ec-abf73c6eb291" data-entity-substitution="canonical" title="Known Exploited Vulnerabilities Catalog" KEV Catalog vulnerabilities /a as part of their vulnerability management practice. CISA will continue to add vulnerabilities to the catalog that meet the a href="https://www.cisa.gov/known-exploited-vulnerabilities" data-entity-type="node" data-entity-uuid="f2adba9a-0404-494c-a90c-4363a4a5c934" data-entity-substitution="canonical" title="Reducing the Significant Risk of Known Exploited Vulnerabilities" specified criteria /a . nbsp; /p

404 Media has a story about Proton Mail giving subscriber data to the Swiss government, who passed the information to the FBI. It’s metadata—payment information related to a particular account—but still important knowledge. This sort of thing happens, even to privacy-centric companies like Proton Mail.

Yesterday, I discovered a malicious Bash script that installs a GSocket backdoor on the victim s computer. I don t know the source of the script not how it is delivered to the victim. GSocket[ 1 ] is a networking tool, but also a relay infrastructure, that enables direct, peer-to-peer style communication between systems using a shared secret instead of IP addresses or open ports. It works by having both sides connect outbound to a global relay network. Tools like gs-netcat can provide remote shells, file transfer, or tunneling and bypass classic security controls. The script that I found uses a copy of gs-netcat but the way it implements persistence and anti-forensic techniques deserves a review. A few weeks ago, I found a sample that used GSocket connectivity as a C2 channel. It makes me curious and I started to hunt for more samples. Bingo! The new one that I found (SHA256:6ce69f0a0db6c5e1479d2b05fb361846957f5ad8170f5e43c7d66928a43f3286[ 2 ]) has been detected by only 17 antivirus solutions on VT. The script is not obfuscated and even has comments so I think that it was uploaded on VT for testing purposes by the developper (just a guess) Let s have a look at the techniques used. When you execute it in a sandbox, you see this: Note the identification of the tool ( G-Socket Bypass Stealth ) and the reference to @bboscat [ 3 ] A GSocket client is downloaded, started and is talking to the following IP: The malware implements persistence through different well-known techniques on Linux. First, a cron job is created: Every top-hour, the disguised gs-netcat will be killed (if running) and restarted. To improve persistence, the same code is added to the victim's .profile: The malware itself is copied in .ssh/putty and the GSocket shared secret stored in a fake SSH key file: The ELF file id_rsa (SHA256: d94f75a70b5cabaf786ac57177ed841732e62bdcc9a29e06e5b41d9be567bcfa) is the gs-netcat tool downloaded directly from the G-Socket CDN. Ok, let s have a look at an interesting anti-forensic technique implemented in the Bash script. File operations are not simply performed using classic commands like cp, rm, mv, etc. They are embedded in helper functions with a timestamp tracking/restoration system so the malware can later hide filesystem changes. Here is an example with a function that will create a file: mk_file() { local fn local oldest local pdir local pdir_added fn= $1 local exists # DEBUGF ${CC}MK_FILE($fn)${CN} pdir= $(dirname $fn ) [[ -e $fn ]] exists=1 ts_is_marked $pdir || { # HERE: Parent not tracked _ts_add $pdir NOT BY XMKDIR pdir_added=1 } ts_is_marked $fn || { # HERE: Not yet tracked _ts_get_ts $fn # Do not add creation fails. touch $fn 2 /dev/null || { # HERE: Permission denied [[ -n $pdir_added ]] { # Remove pdir if it was added above # Bash 5.0 does not support arr[-1] # Quote ( ) to silence shellcheck unset _ts_ts_a[${#_ts_ts_a[@]}-1] unset _ts_fn_a[${#_ts_fn_a[@]}-1] unset _ts_mkdir_fn_a[${#_ts_mkdir_fn_a[@]}-1] } return 69 # False } [[

(c) SANS Internet Storm Center. https://isc.sans.edu Creative Commons Attribution-Noncommercial 3.0 United States License.

The U.S. Justice Department joined authorities in Canada and Germany in dismantling the online infrastructure behind four highly disruptive botnets that compromised more than three million Internet of Things (IoT) devices, such as routers and web cameras. The feds say the four botnets — named Aisuru , Kimwolf , JackSkid and Mossad — are responsible for a series of recent record-smashing distributed denial-of-service (DDoS) attacks capable of knocking nearly any target offline. Image: Shutterstock, @Elzicon. The Justice Department said the Department of Defense Office of Inspector General’s (DoDIG) Defense Criminal Investigative Service (DCIS) executed seizure warrants targeting multiple U.S.-registered domains, virtual servers, and other infrastructure involved in DDoS attacks against Internet addresses owned by the DoD. The government alleges the unnamed people in control of the four botnets used their crime machines to launch hundreds of thousands of DDoS attacks, often demanding extortion payments from victims. Some victims reported tens of thousands of dollars in losses and remediation expenses. The oldest of the botnets — Aisuru — issued more than 200,000 attacks commands, while JackSkid hurled at least 90,000 attacks. Kimwolf issued more than 25,000 attack commands, the government said, while Mossad was blamed for roughy 1,000 digital sieges. The DOJ said the law enforcement action was designed to prevent further infection to victim devices and to limit or eliminate the ability of the botnets to launch future attacks. The case is being investigated by the DCIS with help from the FBI’s field office in Anchorage, Alaska, and the DOJ’s statement credits nearly two dozen technology companies with assisting in the operation. “By working closely with DCIS and our international law enforcement partners, we collectively identified and disrupted criminal infrastructure used to carry out large-scale DDoS attacks,” said Special Agent in Charge Rebecca Day of the FBI Anchorage Field Office. Aisuru emerged in late 2024, and by mid-2025 it was launching record-breaking DDoS attacks as it rapidly infected new IoT devices. In October 2025, Aisuru was used to seed Kimwolf, an Aisuru variant which introduced a novel spreading mechanism that allowed the botnet to infect devices hidden behind the protection of the user’s internal network. On January 2, 2026, the security firm Synthient publicly disclosed the vulnerability Kimwolf was using to propagate so quickly. That disclosure helped curtail Kimwolf’s spread somewhat, but since then several other IoT botnets have emerged that effectively copy Kimwolf’s spreading methods while competing for the same pool of vulnerable devices. According to the DOJ, the JackSkid botnet also sought out systems on internal networks just like Kimwolf. The DOJ said its disruption of the four botnets coincided with “law enforcement actions” conducted in Canada and G

iPhone hacking techniques have sometimes been described almost like rare and elusive animals: Hackers have used them so stealthily and carefully against such a small number of hand-picked targets that they're only rarely seen in the wild. Now a recent spate of espionage and cybercriminal campaigns has instead deployed those same phone-takeover tools, embedded in infected websites, to indiscriminately hack phones by the thousands. And one new technique in particular—capable of taking over any of hundreds of millions of iOS devices —has appeared on the web in an easily reusable form, putting a significant fraction of the world's iPhone users at risk. Researchers at Google and cybersecurity firms iVerify and Lookout on Wednesday jointly revealed the discovery of a sophisticated iPhone hacking technique known as DarkSword that they've seen in use on infected websites, capable of instantly and silently hacking iOS devices that visit those sites. While the technique doesn't affect the latest updated versions of iOS, it does work against iOS devices running versions of Apple's previous operating system release, iOS 18, which as of last month still accounted for close to a quarter of iPhones, according to Apple's own count. “A vast number of iOS users could have all of their personal data stolen simply for visiting a popular website,” says Rocky Cole, iVerify's cofounder and CEO. “Hundreds of millions of people who are still using older Apple devices or older operating system versions remain vulnerable.” Read full article Comments

Over the past year, I have had conversations with security leaders across a variety of disciplines, and the energy around AI is undeniable. Organizations are moving fast, and security teams are rising to meet the moment. Time and again, the question comes back to the same thing: “We’re adopting AI fast, how do we make sure our security keeps pace?” Explore the updated Microsoft Zero Trust Workshop and Assessment It’s the right question, and it’s the one we’ve been working to answer by updating the tools and guidance you already rely on. We’re announcing Microsoft’s approach to Zero Trust for AI (ZT4AI). Zero Trust for AI extends proven Zero Trust principles to the full AI lifecycle—from data ingestion and model training to deployment and agent behavior. Today, we’re releasing a new set of tools and guidance to help you move forward with confidence: A new AI pillar in the Zero Trust Workshop . Updated Data and Networking pillars in the Zero Trust Assessment tool. A new Zero Trust reference architecture for AI. Practical patterns and practices for securing AI at scale. Here’s what’s new and how to use it. Why Zero Trust principles must extend to AI AI systems don’t fit neatly into traditional security models. They introduce new trust boundaries—between users and agents, models and data, and humans and automated decision-making. As organizations adopt autonomous and semi-autonomous AI agents, a new class of risk emerges: agents that are overprivileged, manipulated, or misaligned can act like “double agents,” working against the very outcomes they were built to support. Watch the video: AI with Zero Trust Security By applying three foundational principles of Zero Trust to AI: Verify explicitly —Continuously evaluate the identity and behavior of AI agents, workloads, and users. Apply least privilege —Restrict access to models, prompts, plugins, and data sources to only what’s needed. Assume breach —Design AI systems to be resilient to prompt injection, data poisoning, and lateral movement. These aren’t new principles. What’s new is how we apply them systematically to AI environments. A unified journey: Strategy → assessment → implementation The most common challenge we hear from security leaders and practitioners is a lack of a clear, structured path from knowing what to do to doing it. That’s what Microsoft’s approach to Zero Trust for AI is designed to solve—to help you get to next steps and actions, quickly. Zero Trust Workshop—now with an AI pillar Building on last year’s announcement , the Zero Trust Workshop has been updated with a dedicated AI pillar, now covering 700 security controls across 116 logical groups and 33 functional swim lanes. It is scenario-based and prescriptive, designed to move teams from assessment to execution with clarity and speed. The workshop helps organizations: Align security, IT, and business stakeholders on sha