Search results for Agent Actions | Breaking Cybersecurity News | The Hacker News

Run by the team at workflow orchestration and AI platform Tines, the Tines library features over 1,000 pre-built workflows shared by security practitioners from across the community - all free to import and deploy through the platform's Community Edition. The workflow we are highlighting streamlines security alert handling by automatically identifying and executing the appropriate Standard Operating Procedures (SOPs) from Confluence. When an alert triggers, AI agents analyze it, locate relevant SOPs, and perform required remediation steps - all while keeping the on-call team informed via Slack. It was created by Michael Tolan, Security Researcher L2 at Tines, and Peter Wrenn, Senior Solutions Engineer at Tines. In this guide, we'll share an overview of the workflow, plus step-by-step instructions for getting it up and running. The problem - manual alert triage and SOP execution For security teams, responding to alerts efficiently requires quickly identifying the threat ty...

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...

Malicious actors can exploit default configurations in ServiceNow's Now Assist generative artificial intelligence (AI) platform and leverage its agentic capabilities to conduct prompt injection attacks. The second-order prompt injection, according to AppOmni, makes use of Now Assist's agent-to-agent discovery to execute unauthorized actions, enabling attackers to copy and exfiltrate sensitive corporate data, modify records, and escalate privileges. "This discovery is alarming because it isn't a bug in the AI; it's expected behavior as defined by certain default configuration options," said Aaron Costello, chief of SaaS Security Research at AppOmni. "When agents can discover and recruit each other, a harmless request can quietly turn into an attack, with criminals stealing sensitive data or gaining more access to internal company systems. These settings are easy to overlook." The attack is made possible because of agent discovery and agent-to-a...

AI agents are rapidly becoming a core part of the enterprise, being embedded across enterprise workflows, operating with autonomy, and making decisions about which systems to access and how to use them. But as agents grow in power and autonomy, so do the risks and threats.  Recent studies show 80% of companies have already experienced unintended AI agent actions, from unauthorized system access to data leaks. These incidents aren't edge cases. They are the inevitable outcome of deploying AI agents at scale without purpose-built security mechanisms. Traditional IAM wasn't designed for this. Agents move too fast, operate 24/7, while relying on non-human identities (NHIs) to define precisely what they can and can't do. How can organizations possibly secure what they cannot see or control? To address this challenge, a new approach is needed—one that enables secure-by-design AI agent deployment across the enterprise. Enter: Astrix's Agent Control Plane (ACP) Astrix's AI Agent Cont...

AI agents promise to automate everything from financial reconciliations to incident response. Yet every time an AI agent spins up a workflow, it has to authenticate somewhere; often with a high-privilege API key, OAuth token, or service account that defenders can't easily see. These "invisible" non-human identities (NHIs) now outnumber human accounts in most cloud environments, and they have become one of the ripest targets for attackers. Astrix's Field CTO Jonathan Sander put it bluntly in a recent Hacker News webinar : "One dangerous habit we've had for a long time is trusting application logic to act as the guardrails. That doesn't work when your AI agent is powered by LLMs that don't stop and think when they're about to do something wrong. They just do it." Why AI Agents Redefine Identity Risk Autonomy changes everything: An AI agent can chain multiple API calls and modify data without a human in the loop. If the underlying credential is exposed or overprivileged, each addit...

ChatGPT and similar large language models (LLMs) have added further complexity to the ever-growing online threat landscape. Cybercriminals no longer need advanced coding skills to execute fraud and other damaging attacks against online businesses and customers, thanks to bots-as-a-service, residential proxies, CAPTCHA farms, and other easily accessible tools.  Now, the latest technology damaging businesses' bottom line is  ChatGPT . Not only have ChatGPT, OpenAI, and other LLMs raised ethical issues by  training their models  on scraped data from across the internet. LLMs are negatively impacting enterprises' web traffic, which can be extremely damaging to business.  3 Risks Presented by LLMs, ChatGPT, & ChatGPT Plugins Among the threats ChatGPT and ChatGPT plugins can pose against online businesses, there are three key risks we will focus on: Content theft  (or republishing data without permission from the original source)can hurt the authority,...

The newly released OpenAI ChatGPT Atlas web browser has been found to be susceptible to a prompt injection attack where its omnibox can be jailbroken by disguising a malicious prompt as a seemingly harmless URL to visit. "The omnibox (combined address/search bar) interprets input either as a URL to navigate to, or as a natural-language command to the agent," NeuralTrust said in a report published Friday. "We've identified a prompt injection technique that disguises malicious instructions to look like a URL, but that Atlas treats as high-trust 'user intent' text, enabling harmful actions." Last week, OpenAI launched Atlas as a web browser with built-in ChatGPT capabilities to assist users with web page summarization, inline text editing, and agentic functions. In the attack outlined by the artificial intelligence (AI) security company, an attacker can take advantage of the browser's lack of strict boundaries between trusted user input and untru...

Citrix has released security updates for a high-severity security flaw impacting NetScaler Console (formerly NetScaler ADM) and NetScaler Agent that could lead to privilege escalation under certain conditions. The vulnerability, tracked as CVE-2024-12284 , has been given a CVSS v4 score of 8.8 out of a maximum of 10.0. It has been described as a case of improper privilege management that could result in authenticated privilege escalation if the NetScaler Console Agent is deployed and allows an attacker to execute post-compromise actions. "The issue arises due to inadequate privilege management and could be exploited by an authenticated malicious actor to execute commands without additional authorization," Netscaler noted . "However, only authenticated users with existing access to the NetScaler Console can exploit this vulnerability, thereby limiting the threat surface to only authenticated users." The shortcoming affects the below versions - NetScaler Cons...

Cybersecurity researchers have disclosed details of a now-patched security flaw in the Amazon EC2 Simple Systems Manager (SSM) Agent that, if successfully exploited, could permit an attacker to achieve privilege escalation and code execution. The vulnerability could permit an attacker to create directories in unintended locations on the filesystem, execute arbitrary scripts with root privileges, and likely escalate privileges or perform malicious activities by writing files to sensitive areas of the system, Cymulate said in a report shared with The Hacker News. Amazon SSM Agent is a component of Amazon Web Services (AWS) that enables administrators to remotely manage, configure, and execute commands on EC2 instances and on-premises servers.  The software processes commands and tasks defined in SSM Documents , which can include one or more plugins, each of which is responsible for carrying out specific tasks, such as running shell scripts or automating deployment or configura...

AI agents have rapidly evolved from experimental technology to essential business tools. The OWASP framework explicitly recognizes that Non-Human Identities play a key role in agentic AI security. Their analysis highlights how these autonomous software entities can make decisions, chain complex actions together, and operate continuously without human intervention. They're no longer just tools, but an integral and significant part of your organization's workforce. Consider this reality: Today's AI agents can analyze customer data, generate reports, manage system resources, and even deploy code, all without a human clicking a single button. This shift represents both tremendous opportunity and unprecedented risk. AI Agents are only as secure as their NHIs Here's what security leaders are not necessarily considering: AI agents don't operate in isolation . To function, they need access to data, systems, and resources. This highly privileged, often overlooked acces...

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...

Organizations struggle to find ways to keep a good security posture. This is because it is difficult to create secure system policies and find the right tools that help achieve a good posture. In many cases, organizations work with tools that do not integrate with each other and are expensive to purchase and maintain. Security posture management is a term used to describe the process of identifying and mitigating security misconfigurations and compliance risks in an organization. To maintain a good security posture, organizations should at least do the following: Maintain inventory:  Asset inventory is considered first because it provides a comprehensive list of all IT assets that should be protected. This includes the hardware devices, applications, and services that are being used. Perform vulnerability assessment:  The next step is to perform a vulnerability assessment to identify weaknesses in applications and services. Knowledge of the vulnerabilities help to priorit...