AI Security | Breaking Cybersecurity News | The Hacker News

Cybersecurity researchers have disclosed a now-patched security flaw in LangChain's LangSmith platform that could be exploited to capture sensitive data, including API keys and user prompts. The vulnerability, which carries a CVSS score of 8.8 out of a maximum of 10.0, has been codenamed AgentSmith by Noma Security. LangSmith is an observability and evaluation platform that allows users to develop, test, and monitor large language model (LLM) applications, including those built using LangChain. The service also offers what's called a LangChain Hub , which acts as a repository for all publicly listed prompts, agents, and models. "This newly identified vulnerability exploited unsuspecting users who adopt an agent containing a pre-configured malicious proxy server uploaded to 'Prompt Hub,'" researchers Sasi Levi and Gal Moyal said in a report shared with The Hacker News. "Once adopted, the malicious proxy discreetly intercepted all user communicatio...

Cybersecurity researchers have called attention to a new campaign that's actively exploiting a recently disclosed critical security flaw in Langflow to deliver the Flodrix botnet malware. "Attackers use the vulnerability to execute downloader scripts on compromised Langflow servers, which in turn fetch and install the Flodrix malware," Trend Micro researchers Aliakbar Zahravi, Ahmed Mohamed Ibrahim, Sunil Bharti, and Shubham Singh said in a technical report published today. The activity entails the exploitation of CVE-2025-3248 (CVSS score: 9.8), a missing authentication vulnerability in Langflow , a Python-based "visual framework" for building artificial intelligence (AI) applications. Successful exploitation of the flaw could enable unauthenticated attackers to execute arbitrary code via crafted HTTP requests. It was patched by Langflow in March 2025 with version 1.3.0. Last month, the U.S. Cybersecurity and Infrastructure Security Agency (CISA) flagg...

Cybersecurity researchers from  SafeDep and Veracode detailed a number of malware-laced npm packages that are designed to execute remote code and download additional payloads. The packages in question are listed below - eslint-config-airbnb-compat (676 Downloads) ts-runtime-compat-check (1,588 Downloads) solders (983 Downloads) @mediawave/lib (386 Downloads) All the identified npm packages have since been taken down from npm, but not before they were downloaded hundreds of times from the package registry.  SafeDep's analysis of eslint-config-airbnb-compat found that the JavaScript library has ts-runtime-compat-check listed as a dependency, which, in turn, contacts an external server defined in the former package ("proxy.eslint-proxy[.]site") to retrieve and execute a Base64-encoded string. The exact nature of the payload is unknown. "It implements a multi-stage remote code execution attack using a transitive dependency to hide the malicious code,"...

Human identities management and control is pretty well done with its set of dedicated tools, frameworks, and best practices. This is a very different world when it comes to Non-human identities also referred to as machine identities. GitGuardian's end-to-end NHI security platform is here to close the gap. Enterprises are Losing Track of Their Machine Identities Machine identities–service accounts, API keys, bots, automation, and workload identities–that now outnumber humans by up to 100:1 are in fact a massive blind spot in companies' security landscape: Without robust governance, NHIs become a prime target for attackers. Orphaned credentials, over-privileged accounts, and "zombie" secrets are proliferating—especially as organizations accelerate cloud adoption, integrate AI-powered agents, and automate their infrastructure . Secrets Sprawl: The New Attack Surface GitGuardian's research shows that 70% of valid secrets detected in public repositories in 2022 remained active in ...

Security teams face growing demands with more tools, more data, and higher expectations than ever. Boards approve large security budgets, yet still ask the same question: what is the business getting in return? CISOs respond with reports on controls and vulnerability counts – but executives want to understand risk in terms of financial exposure, operational impact, and avoiding loss. The disconnect has become difficult to ignore. The average cost of a breach has reached $4.88 million, according to recent IBM data . That figure reflects not just incident response but also downtime, lost productivity, customer attrition, and the extended effort required to restore operations and trust. The fallout is rarely confined to security. Security leaders need a model that brings those consequences into view before they surface. A Business Value Assessment (BVA) offers that model. It links exposures to cost, prioritization to return, and prevention to tangible value. This article will explain ...

Traditional data leakage prevention (DLP) tools aren't keeping pace with the realities of how modern businesses use SaaS applications. Companies today rely heavily on SaaS platforms like Google Workspace, Salesforce, Slack, and generative AI tools, significantly altering the way sensitive information is handled. In these environments, data rarely appears as traditional files or crosses networks in ways endpoint or network-based DLP tools can monitor. Yet, most companies continue using legacy DLP systems, leaving critical security gaps. A new white paper, Rethinking DLP For The SaaS Era: Why Browser-Centric DLP is the New Mandate , identifies precisely why current DLP methods struggle to secure modern SaaS-driven workflows. It also explores how browser-native security addresses these gaps by focusing security efforts exactly where user interactions occur, in the browser. Why Traditional DLP Tools Fall Short Traditional DLP solutions were built for a simpler time when sensitive...

Several malicious packages have been uncovered across the npm, Python, and Ruby package repositories that drain funds from cryptocurrency wallets, erase entire codebases after installation, and exfiltrate Telegram API tokens, once again demonstrating the variety of supply chain threats lurking in open-source ecosystems. The findings come from multiple reports published by Checkmarx, ReversingLabs, Safety, and Socket in recent weeks. The list of identified packages across these platforms are listed below - Socket noted that the two malicious gems were published by a threat actor under the aliases Bùi nam, buidanhnam, and si_mobile merely days after Vietnam ordered a nationwide ban on the Telegram messaging app late last month for allegedly not cooperating with the government to tackle illicit activities related to fraud, drug trafficking, and terrorism. "These gems silently exfiltrate all data sent to the Telegram API by redirecting traffic through a command-and-control (C2...

Continuous Threat Exposure Management (CTEM) has moved from concept to cornerstone, solidifying its role as a strategic enabler for CISOs. No longer a theoretical framework, CTEM now anchors today's cybersecurity programs by continuously aligning security efforts with real-world risk. At the heart of CTEM is the integration of Adversarial Exposure Validation (AEV), an advanced, offensive methodology powered by proactive security tools including External Attack Surface Management (ASM), autonomous penetration testing and red teaming, and Breach and Attack Simulation (BAS). Together, these AEV tools transform how enterprises proactively identify, validate, and reduce risks, turning threat exposure into a manageable business metric. CTEM reflects a broader evolution in how security leaders measure effectiveness and allocate resources. As board expectations grow and cyber risk becomes inseparable from business risk, CISOs are leveraging CTEM to drive measurable, outcome-based security ...

The cybersecurity landscape has been dramatically reshaped by the advent of generative AI. Attackers now leverage large language models (LLMs) to impersonate trusted individuals and automate these social engineering tactics at scale.  Let's review the status of these rising attacks, what's fueling them, and how to actually prevent, not detect, them.  The Most Powerful Person on the Call Might Not Be Real Recent threat intelligence reports highlight the growing sophistication and prevalence of AI-driven attacks: Voice Phishing Surge: According to CrowdStrike's 2025 Global Threat Report , there was a 442% increase in voice phishing (vishing) attacks between the first and second halves of 2024, driven by AI-generated phishing and impersonation tactics. Social Engineering Prevalence: Verizon's 2025 Data Breach Investigations Report indicates that social engineering remains a top pattern in breaches, with phishing and pretexting accounting for a significant portion of inc...

It wasn't ransomware headlines or zero-day exploits that stood out most in this year's Verizon 2025 Data Breach Investigations Report (DBIR) — it was what fueled them. Quietly, yet consistently, two underlying factors played a role in some of the worst breaches: third-party exposure and machine credential abuse . According to the 2025 DBIR, third-party involvement in breaches doubled year-over-year, jumping from 15% to 30% . In parallel, attackers increasingly exploited machine credentials and ungoverned machine accounts to gain access, escalate privileges, and exfiltrate sensitive data. The message is clear: it's no longer enough to protect your employee users alone. To truly defend against modern threats, organizations must govern all identities — human, non-employee, and machine — within a unified security strategy. Third-Party Risk: Expanding Faster Than Organizations Can Control Today's enterprise is a patchwork of partnerships: contractors, vendors, business p...

How Many Gaps Are Hiding in Your Identity System? It's not just about logins anymore. Today's attackers don't need to "hack" in—they can trick their way in. Deepfakes, impersonation scams, and AI-powered social engineering are helping them bypass traditional defenses and slip through unnoticed. Once inside, they can take over accounts, move laterally, and cause long-term damage—all without triggering alarms. But here's the catch: most organizations only focus on parts of the identity lifecycle—usually authentication. That leaves critical gaps wide open during enrollment, recovery, and even routine access. This upcoming webinar from Beyond Identity and Nametag breaks down what it really takes to protect your entire identity lifecycle —from the first time a user joins, to every login, to the moment they forget their credentials. 🔐 What's Covered: AI Threats Are Already Here – Learn how attackers are using deepfakes to impersonate real users Phishing-Resistant MFA – Go beyond...

Find out how Reco keeps Microsoft 365 Copilot safe by spotting risky prompts, protecting data, managing user access, and identifying threats - all while keeping productivity high. Microsoft 365 Copilot promises to boost productivity by turning natural language prompts into actions. Employees can generate reports, comb through data, or get instant answers just by asking Copilot.  However, alongside this convenience comes serious security concerns. Copilot operates across a company's SaaS apps (from SharePoint to Teams and beyond), which means a careless prompt or a compromised user account could expose troves of sensitive information.  Security experts warn that organizations shouldn't assume default settings will keep them safe. Without proactive controls, every file in your organization could be accessible via Copilot. A malicious actor might use Copilot to discover and exfiltrate confidential data without having to manually search through systems. With the right prom...