Search results for AI Agents Prompt Injection Defense | Breaking Cybersecurity News | The Hacker News

Cybersecurity researchers have disclosed a critical flaw impacting Salesforce Agentforce , a platform for building artificial intelligence (AI) agents, that could allow attackers to potentially exfiltrate sensitive data from its customer relationship management (CRM) tool by means of an indirect prompt injection. The vulnerability has been codenamed ForcedLeak (CVSS score: 9.4) by Noma Security, which discovered and reported the problem on July 28, 2025. It impacts any organization using Salesforce Agentforce with the Web-to-Lead functionality enabled. "This vulnerability demonstrates how AI agents present a fundamentally different and expanded attack surface compared to traditional prompt-response systems," Sasi Levi, security research lead at Noma, said in a report shared with The Hacker News. One of the most severe threats facing generative artificial intelligence (GenAI) systems today is indirect prompt injection , which occurs when malicious instructions are ins...

Microsoft on Tuesday unveiled the expansion of its Sentinel Security Incidents and Event Management solution (SIEM) as a unified agentic platform with the general availability of the Sentinel data lake. In addition, the tech giant said it's also releasing a public preview of Sentinel Graph and Sentinel Model Context Protocol ( MCP ) server to turn telemetry into a security graph and allow AI agents access an organization's security context in a standardized manner. "With graph-based context, semantic access, and agentic orchestration, Sentinel gives defenders a single platform to ingest signals, correlate across domains, and empower AI agents built in Security Copilot, VS Code using GitHub Copilot, or other developer platforms," Vasu Jakkal, corporate vice president at Microsoft Security, said in a post shared with The Hacker News. Microsoft released Sentinel data lake in public preview earlier this July as a purpose-built, cloud-native tool to ingest, manage...

Google has revealed the various safety measures that are being incorporated into its generative artificial intelligence (AI) systems to mitigate emerging attack vectors like indirect prompt injections and improve the overall security posture for agentic AI systems. "Unlike direct prompt injections, where an attacker directly inputs malicious commands into a prompt, indirect prompt injections involve hidden malicious instructions within external data sources," Google's GenAI security team said . These external sources can take the form of email messages, documents, or even calendar invites that trick the AI systems into exfiltrating sensitive data or performing other malicious actions. The tech giant said it has implemented what it described as a "layered" defense strategy that is designed to increase the difficulty, expense, and complexity required to pull off an attack against its systems. These efforts span model hardening, introducing purpose-built mac...

The AI browser wars are coming to a desktop near you, and you need to start worrying about their security challenges. For the last two decades, whether you used Chrome, Edge, or Firefox, the fundamental paradigm remained the same: a passive window through which a human user viewed and interacted with the internet. That era is over. We are currently witnessing a shift that renders the old OS-centric browser debates irrelevant. The new battleground is agentic AI browsers, and for security professionals, it represents a terrifying inversion of the traditional threat landscape. A new webinar dives into the issue of AI browsers , their risks, and how security teams can deal with them. Even today, the browser is the main interface for AI consumption; it is where most users access AI assistants such as ChatGPT or Gemini, use AI-enabled SaaS applications, and engage AI agents. AI providers were the first to recognize this, which is why we've seen a spate of new 'agentic' AI browsers bein...

Artificial intelligence (AI) holds tremendous promise for improving cyber defense and making the lives of security practitioners easier. It can help teams cut through alert fatigue, spot patterns faster, and bring a level of scale that human analysts alone can't match. But realizing that potential depends on securing the systems that make it possible. Every organization experimenting with AI in security operations is, knowingly or not, expanding its attack surface. Without clear governance, strong identity controls, and visibility into how AI makes its decisions, even well-intentioned deployments can create risk faster than they reduce it. To truly benefit from AI, defenders need to approach securing it with the same rigor they apply to any other critical system. That means establishing trust in the data it learns from, accountability for the actions it takes, and oversight for the outcomes it produces. When secured correctly, AI can amplify human capability instead of replacing it t...

As the field of artificial intelligence (AI) continues to evolve at a rapid pace, fresh research has found how techniques that render the Model Context Protocol ( MCP ) susceptible to prompt injection attacks could be used to develop security tooling or identify malicious tools, according to a new report from Tenable. MCP, launched by Anthropic in November 2024, is a framework designed to connect Large Language Models (LLMs) with external data sources and services, and make use of model-controlled tools to interact with those systems to enhance the accuracy, relevance, and utility of AI applications. It follows a client-server architecture, allowing hosts with MCP clients such as Claude Desktop or Cursor to communicate with different MCP servers, each of which exposes specific tools and capabilities. While the open standard offers a unified interface to access various data sources and even switch between LLM providers, they also come with a new set of risks, ranging from exc...

Google on Tuesday revealed that its large language model (LLM)-assisted vulnerability discovery framework identified a security flaw in the SQLite open-source database engine before it could have been exploited in the wild. The vulnerability, tracked as CVE-2025-6965 (CVSS score: 7.2), is a memory corruption flaw affecting all versions prior to 3.50.2. It was discovered by Big Sleep , an artificial intelligence (AI) agent that was launched by Google last year as part of a collaboration between DeepMind and Google Project Zero. "An attacker who can inject arbitrary SQL statements into an application might be able to cause an integer overflow resulting in read off the end of an array," SQLite project maintainers said in an advisory. The tech giant described CVE-2025-6965 as a critical security issue that was "known only to threat actors and was at risk of being exploited." Google did not reveal who the threat actors were. "Through the combination of threa...

Hackers aren't kicking down the door anymore. They just use the same tools we use every day — code packages, cloud accounts, email, chat, phones, and "trusted" partners — and turn them against us. One bad download can leak your keys. One weak vendor can expose many customers at once. One guest invite, one link on a phone, one bug in a common tool, and suddenly your mail, chats, repos, and servers are in play. Every story below is a reminder that your "safe" tools might be the real weak spot. ⚡ Threat of the Week Shai-Hulud Returns with More Aggression — The npm registry was targeted a second time by a self-replicating worm that went by the moniker "Sha1-Hulud: The Second Coming," affecting over 800 packages and 27,000 GitHub repositories. Like in the previous iteration, the main objective was to steal sensitive data like API keys, cloud credentials, and npm and GitHub authentication information, and facilitate deeper supply chain compromise in a worm-like fashion. Th...

It's getting harder to tell where normal tech ends and malicious intent begins. Attackers are no longer just breaking in — they're blending in, hijacking everyday tools, trusted apps, and even AI assistants. What used to feel like clear-cut "hacker stories" now looks more like a mirror of the systems we all use. This week's findings show a pattern: precision, patience, and persuasion. The newest campaigns don't shout for attention — they whisper through familiar interfaces, fake updates, and polished code. The danger isn't just in what's being exploited, but in how ordinary it all looks. ThreatsDay pulls these threads together — from corporate networks to consumer tech — revealing how quiet manipulation and automation are reshaping the threat landscape. It's a reminder that the future of cybersecurity won't hinge on bigger walls, but on sharper awareness. Open-source tool exploited Abuse of Nezha for Post-Exploitation Bad actors are le...

The year opened without a reset. The same pressure carried over, and in some places it tightened. Systems people assume are boring or stable are showing up in the wrong places. Attacks moved quietly, reused familiar paths, and kept working longer than anyone wants to admit. This week's stories share one pattern. Nothing flashy. No single moment. Just steady abuse of trust — updates, extensions, logins, messages — the things people click without thinking. That's where damage starts now. This recap pulls those signals together. Not to overwhelm, but to show where attention slipped and why it matters early in the year. ⚡ Threat of the Week RondoDox Botnet Exploits React2Shell Flaw — A persistent nine-month-long campaign has targeted Internet of Things (IoT) devices and web applications to enroll them into a botnet known as RondoDox. As of December 2025, the activity has been observed leveraging the recently disclosed React2Shell (CVE-2025-55182, CVSS score: 10.0) flaw as an initial...

Cybersecurity never slows down. Every week brings new threats, new vulnerabilities, and new lessons for defenders. For security and IT teams, the challenge is not just keeping up with the news—it's knowing which risks matter most right now. That's what this digest is here for: a clear, simple briefing to help you focus where it counts. This week, one story stands out above the rest: the Salesloft–Drift breach, where attackers stole OAuth tokens and accessed Salesforce data from some of the biggest names in tech. It's a sharp reminder of how fragile integrations can become the weak link in enterprise defenses. Alongside this, we'll also walk through several high-risk CVEs under active exploitation, the latest moves by advanced threat actors, and fresh insights on making security workflows smarter, not noisier. Each section is designed to give you the essentials—enough to stay informed and prepared, without getting lost in the noise. ⚡ Threat of the Week Salesloft to Take Drift Of...

What if attackers aren't breaking in—they're already inside, watching, and adapting? This week showed a sharp rise in stealth tactics built for long-term access and silent control. AI is being used to shape opinions. Malware is hiding inside software we trust. And old threats are returning under new names. The real danger isn't just the breach—it's not knowing who's still lurking in your systems. If your defenses can't adapt quickly, you're already at risk. Here are the key cyber events you need to pay attention to this week. ⚡ Threat of the Week Lemon Sandstorm Targets Middle East Critical Infra — The Iranian state-sponsored threat group tracked as Lemon Sandstorm targeted an unnamed critical national infrastructure (CNI) in the Middle East and maintained long-term access that lasted for nearly two years using custom backdoors like HanifNet, HXLibrary, and NeoExpressRAT. The activity, which lasted from at least May 2023 to February 2025, entailed "extensive es...

Cybersecurity today moves at the pace of global politics. A single breach can ripple across supply chains, turn a software flaw into leverage, or shift who holds the upper hand. For leaders, this means defense isn't just a matter of firewalls and patches—it's about strategy. The strongest organizations aren't the ones with the most tools, but the ones that see how cyber risks connect to business, trust, and power. This week's stories highlight how technical gaps become real-world pressure points—and why security decisions now matter far beyond IT. ⚡ Threat of the Week Popular Password Managers Affected by Clickjacking — Popular password manager plugins for web browsers have been found susceptible to clickjacking security vulnerabilities that could be exploited to steal account credentials, two-factor authentication (2FA) codes, and credit card details under certain conditions. The technique has been dubbed Document Object Model (DOM)-based extension clickjacking by independent sec...

This week saw a lot of new cyber trouble. Hackers hit Fortinet and Chrome with new 0-day bugs. They also broke into supply chains and SaaS tools. Many hid inside trusted apps, browser alerts, and software updates. Big firms like Microsoft, Salesforce, and Google had to react fast — stopping DDoS attacks, blocking bad links, and fixing live flaws. Reports also showed how fast fake news, AI risks, and attacks on developers are growing. Here's what mattered most in security this week. ⚡ Threat of the Week Fortinet Warns of Another Silently Patched and Actively Exploited FortiWeb Flaw — Fortinet has warned that a new security flaw in FortiWeb has been exploited in the wild. The medium-severity vulnerability, tracked as CVE-2025-58034, carries a CVSS score of 6.7 out of a maximum of 10.0. It has been addressed in version 8.0.2. "An Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection') vulnerability [CWE-78] in FortiWeb may allow an a...

It's been a week of chaos in code and calm in headlines. A bug that broke the internet's favorite framework, hackers chasing AI tools, fake apps stealing cash, and record-breaking cyberattacks — all within days. If you blink, you'll miss how fast the threat map is changing. New flaws are being found, published, and exploited in hours instead of weeks. AI-powered tools meant to help developers are quickly becoming new attack surfaces. Criminal groups are recycling old tricks with fresh disguises — fake apps, fake alerts, and fake trust. Meanwhile, defenders are racing to patch systems, block massive DDoS waves, and uncover spy campaigns hiding quietly inside networks. The fight is constant, the pace relentless. For a deeper look at these stories, plus new cybersecurity tools and upcoming expert webinars, check out the full ThreatsDay Bulletin. ⚡ Threat of the Week Max Severity React Flaw Comes Under Attack — A critical security flaw impacting React Server Components (RSC) has ...

This week, cyber attackers are moving quickly, and businesses need to stay alert. They're finding new weaknesses in popular software and coming up with clever ways to get around security. Even one unpatched flaw could let attackers in, leading to data theft or even taking control of your systems. The clock is ticking—if defenses aren't updated regularly, it could lead to serious damage. The message is clear: don't wait for an attack to happen. Take action now to protect your business. Here's a look at some of the biggest stories in cybersecurity this week: from new flaws in WinRAR and NVIDIA Triton to advanced attack techniques you should know about. Let's get into the details. ⚡ Threat of the Week Trend Micro Warns of Actively Exploited 0-Day — Trend Micro has released temporary mitigations to address critical security flaws in on-premise versions of Apex One Management Console that it said have been exploited in the wild. The vulnerabilities (CVE-2025-54948 and CVE-2025-54987),...

Cyber threats don't show up one at a time anymore. They're layered, planned, and often stay hidden until it's too late. For cybersecurity teams, the key isn't just reacting to alerts—it's spotting early signs of trouble before they become real threats. This update is designed to deliver clear, accurate insights based on real patterns and changes we can verify. With today's complex systems, we need focused analysis—not noise. What you'll see here isn't just a list of incidents, but a clear look at where control is being gained, lost, or quietly tested. ⚡ Threat of the Week Lumma Stealer, DanaBot Operations Disrupted — A coalition of private sector companies and law enforcement agencies have taken down the infrastructure associated with Lumma Stealer and DanaBot . Charges have also been unsealed against 16 individuals for their alleged involvement in the development and deployment of DanaBot. The malware is equipped to siphon data from victim computers, hijack banking session...

Some of the biggest security problems start quietly. No alerts. No warnings. Just small actions that seem normal but aren't. Attackers now know how to stay hidden by blending in, and that makes it hard to tell when something's wrong. This week's stories aren't just about what was attacked—but how easily it happened. If we're only looking for the obvious signs, what are we missing right in front of us? Here's a look at the tactics and mistakes that show how much can go unnoticed. ⚡ Threat of the Week Apple Zero-Click Flaw in Messages Exploited to Deliver Paragon Spyware — Apple disclosed that a security flaw in its Messages app was actively exploited in the wild to target civil society members in sophisticated cyber attacks. The vulnerability, CVE-2025-43200, was addressed by the company in February as part of iOS 18.3.1, iPadOS 18.3.1, iPadOS 17.7.5, macOS Sequoia 15.3.1, macOS Sonoma 14.7.4, macOS Ventura 13.7.4, watchOS 11.3.1, and visionOS 2.3.1. The Citizen Lab said it u...

The cyber world never hits pause, and staying alert matters more than ever. Every week brings new tricks, smarter attacks, and fresh lessons from the field. This recap cuts through the noise to share what really matters—key trends, warning signs, and stories shaping today's security landscape. Whether you're defending systems or just keeping up, these highlights help you spot what's coming before it lands on your screen. ⚡ Threat of the Week Oracle 0-Day Under Attack — Threat actors with ties to the Cl0p ransomware group have exploited a zero-day flaw in E-Business Suite to facilitate data theft attacks. The vulnerability, tracked as CVE-2025-61882 (CVSS score: 9.8), concerns an unspecified bug that could allow an unauthenticated attacker with network access via HTTP to compromise and take control of the Oracle Concurrent Processing component. In a post shared on LinkedIn, Charles Carmakal, CTO of Mandiant at Google Cloud, said "Cl0p exploited multiple vulnerabilities in Ora...

Malware isn't just trying to hide anymore—it's trying to belong. We're seeing code that talks like us, logs like us, even documents itself like a helpful teammate. Some threats now look more like developer tools than exploits. Others borrow trust from open-source platforms, or quietly build themselves out of AI-written snippets. It's not just about being malicious—it's about being believable. In this week's cybersecurity recap, we explore how today's threats are becoming more social, more automated, and far too sophisticated for yesterday's instincts to catch. ⚡ Threat of the Week Secret Blizzard Conduct ISP-Level AitM Attacks to Deploy ApolloShadow — Russian cyberspies are abusing local internet service providers' networks to target foreign embassies in Moscow and likely collect intelligence from diplomats' devices. The activity has been attributed to the Russian advanced persistent threat (APT) known as Secret Blizzard (aka Turla). It likely involves using an adversary-...