Tenable Jailbreaks GPT-5, Gets It To Generate Dangerous Info Despite OpenAI’s New Safety Tech
Within just 24 hours of the release of OpenAI’s GPT-5, Tenable Research successfully managed to jailbreak the model by getting it to share detailed instructions for how to build an explosive. Our finding is concerning, given that OpenAI described GPT-5's prompt safety technology as significantly…
The AI Security Dilemma: Navigating the High-Stakes World of Cloud AI
AI presents an incredible opportunity for organizations even as it expands the attack surface in new and complex ways. For security leaders, the goal isn't to stop AI adoption but to enable it securely.
Introduzione a Tenable AI Exposure: non tirare più a indovinare, inizia a proteggere la superficie di attacco dell'IA
Ora disponibile in Tenable One, Tenable AI Exposure offre visibilità su come i tuoi team utilizzano le piattaforme di IA e sui punti in cui tale utilizzo potrebbe mettere a rischio i tuoi dati, gli utenti e le difese.
CVE-2025-54135, CVE-2025-54136: Frequently Asked Questions About Vulnerabilities in Cursor IDE (CurXecute and MCPoison)
Researchers have disclosed two vulnerabilities in Cursor, the popular AI-assisted code editor, that impact its handling of model context protocol (MCP) servers, which could be used to gain code execution on vulnerable systems.
The White House AI Action Plan: A Critical Opportunity to Secure the Future
AI without built-in cybersecurity remains a liability. The AI Action Plan presents a pivotal opportunity to get this right by emphasizing a secure-by-design approach.
Cybersecurity Snapshot: AI Security Trails AI Usage, Putting Data at Risk, IBM Warns, as OWASP Tackles Agentic AI App Security
Check out fresh insights on AI data security from IBM’s “Cost of a Data Breach Report 2025.” Plus, OWASP issues guide on securing Agentic AI apps. In addition, find out how to protect your org against the Scattered Spider cyber crime group. And get the latest on zero-trust microsegmentation;…
Cybersecurity Snapshot: SharePoint Attacks Trigger Urgent Patching Calls, While U.S. Gov’t Unveils AI Innovation Plan
Check out the latest on attackers’ cyber siege of SharePoint servers. Plus, the White House releases plan to spur AI innovation. In addition, CISA alerts orgs about Interlock ransomware. And get the latest on Q2's top malware; ransomware trends; and credentialed scanning.
Tackling Shadow AI in Cloud Workloads
As enterprise adoption of cloud AI systems balloons, protecting them has become a priority. Shadow AI – the unsanctioned use of AI apps – has emerged as a particularly critical threat. Here we outline two best practices that can help you combat shadow AI in your cloud workloads.
Cybersecurity Snapshot: AI Security Tools Embraced by Cyber Teams, Survey Finds, as Vulnerability Research Gets a Boost from UK Cyber Agency
Check out why AI security tools are turning into “must have” assets for cyber teams. Plus, get the details on the NCSC’s efforts to supercharge its bug hunting capabilities. Meanwhile, Tenable webinar attendees shared their experience securing machine identities. And get the latest on the crypto…
Cybersecurity Snapshot: AI Security Field Gets Boost from New CSA Framework and from SANS - OWASP Partnership
Check out a new Cloud Security Alliance framework for securing AI systems. Plus, SANS Institute and OWASP are joining forces to deliver AI security controls. Meanwhile, Accenture finds orgs unprepared to counter AI-powered cyber attacks. And get the latest on the Iran cyber threat, SMB cyber…
How Tenable Research Discovered a Critical Remote Code Execution Vulnerability on Anthropic MCP Inspector
Tenable Research recently discovered a critical vulnerability impacting Anthropic's MCP Inspector tool, a core element of the MCP ecosystem. In this blog, we provide details on how we discovered the vulnerability in this widely used open-source tool — and what users can do about it..
AI Security: Web Flaws Resurface in Rush to Use MCP Servers
In the rush to implement AI tools and services, developers are rapidly embracing the Model Context Protocol (MCP). In the process, classic vulnerabilities are resurfacing and new ones are being introduced. In this blog, we outline key areas of concern and how Tenable Web App Scanning can help.