HackMyIP

Cybersecurity News

Latest updates from top security sources

2026-06-27The Hacker News
OpenAI Launches GPT-5.6 Sol Preview With Hardened Cyber Safeguards

OpenAI on Friday rolled out a limited preview of GPT-5.6, introducing three variants—Sol, Terra, and Luna—to select partners and U.S. government agencies. Sol serves as the new fla...

AI SecurityLLM SecurityVulnerability
Read More → Use Tool →
2026-06-15Dark Reading
Copilot SearchLeak Bug Enabled 1-Click Data Theft via Hidden URLs

Microsoft has patched a critical vulnerability in its Copilot AI assistant that allowed attackers to steal sensitive user data—including emails, contact lists, and personal files—t...

AI SecurityAI ThreatsLLM Security
Read More → Use Tool →
2026-06-15The Hacker News
Critical LiteLLM Flaw Chain Lets Low-Privilege Users Hijack AI Gateways

Researchers at Obsidian Security have disclosed a three-vulnerability chain in LiteLLM, a widely deployed open-source AI gateway that brokers calls to more than 100 model providers...

VulnerabilityAI SecurityLLM Security
Read More → Use Tool →
2026-06-13The Hacker News
U.S. Orders Anthropic to Halt Fable 5 and Mythos 5 Access for Foreign Users

Anthropic announced on Friday that it will abruptly disable its most advanced AI models, Claude Fable 5 and Mythos 5, for all users after the U.S. government issued an export contr...

AI SecurityRegulationLLM Security
Read More → Use Tool →
2026-06-12Dark Reading
Anthropic's Claude Mythos 5 & Fable 5: What Security Teams Need to Know

Anthropic has clarified the distinction between its latest large language model releases, confirming that Claude Mythos 5 does not represent a fundamental shift in the security pos...

AI SecurityLLM SecurityRegulation
Read More → Use Tool →
2026-06-12SecurityWeek
Claude Fable 5 Launch Sparks Debate on AI Cyber Risks and Defenses

Anthropic has released Claude Fable 5 as a generally available Mythos-class AI model, implementing safeguards that automatically downgrade the system to the less capable Claude Opu...

AI SecurityAI ThreatsLLM Security
Read More → Use Tool →
2026-06-11The Hacker News
OpenClaw AI Agent Flaws Let Attackers Run Code and Steal Data

Two independent security teams have disclosed serious weaknesses in OpenClaw, a popular self-hosted AI agent, showing how ordinary-looking inputs can be weaponized to execute attac...

AI SecurityLLM SecurityVulnerability
Read More → Use Tool →
2026-06-10BleepingComputer
Anthropic Rolls Out Claude Fable 5 With New AI Safeguards

Anthropic has begun rolling out Claude Fable 5, a new AI model built on the same foundation as its powerful Mythos class. When Anthropic first unveiled Mythos, the company warned t...

AI SecurityLLM SecurityVulnerability
Read More → Use Tool →
2026-06-09The Hacker News
AI Worm Uses Local LLMs to Spread Across Networks Without APIs

Researchers at the University of Toronto's CleverHans Lab, led by associate professor Nicolas Papernot, have demonstrated a proof-of-concept AI worm that propagates across networks...

AI ThreatsLLM SecurityMalware
Read More → Use Tool →
2026-06-09The Hacker News
CISA Adds LiteLLM Command Injection Flaw to KEV After Wild Exploitation

The U.S. Cybersecurity and Infrastructure Security Agency (CISA) has added a high-severity command injection vulnerability in BerriAI LiteLLM to its Known Exploited Vulnerabilities...

VulnerabilityLLM SecurityAI Security
Read More → Use Tool →
2026-06-07BleepingComputer
Microsoft's Intelligent Terminal Brings AI Agents to Windows Command Line

Microsoft has released Intelligent Terminal, an open-source fork of Windows Terminal that embeds AI agents directly into the command-line workflow without disrupting the active she...

AI SecurityLLM Security
Read More → Use Tool →
2026-06-06The Hacker News
OpenAI Rolls Out ChatGPT Lockdown Mode to Block Data Exfiltration

OpenAI has begun deploying a new Lockdown Mode for ChatGPT, targeting personal accounts on Free, Go, Plus, Pro, and self-serve ChatGPT Business plans. The feature is designed for u...

AI SecurityLLM SecurityPrivacy
Read More → Use Tool →
2026-05-29The Hacker News
ChatGPhish Vulnerability Exposes ChatGPT to Phishing Attacks

Security researchers at Permiso Security have uncovered a critical vulnerability in OpenAI's ChatGPT, dubbed ChatGPhish, that transforms the AI assistant's web summarization featur...

VulnerabilityLLM SecurityPhishing
Read More → Use Tool →
2026-05-29The Hacker News
LLM Agent Used in Post-Exploitation After Marimo CVE-2026-39987 Exploit

Sysdig researchers have documented a sophisticated cyberattack where threat actors deployed a large language model (LLM) agent to automate post-exploitation activities following th...

LLM SecurityVulnerabilityCloud Security
Read More → Use Tool →
2026-05-20The Hacker News
Microsoft Open-Sources RAMPART and Clarity for AI Agent Security Testing

Microsoft has unveiled two new open-source security tools—RAMPART and Clarity—to help developers identify and mitigate vulnerabilities in AI agents during the development lifecycle...

AI SecurityLLM Security
Read More → Use Tool →
2026-05-10The Hacker News
Ollama Memory Leak Vulnerability Allows Remote Process Memory Exposure

Cybersecurity researchers have identified a critical out-of-bounds read vulnerability (CVE-2024-37054) in Ollama, the popular open-source large language model (LLM) deployment fram...

VulnerabilityLLM SecurityZero-Day
Read More → Use Tool →
2026-05-08SecurityWeek
Claude Chrome Extension Flaw Allows Attackers to Hijack AI Agent

Security researchers at Cisco Talos have disclosed a critical flaw in the Claude Chrome extension (version 2.3.0) that lets remote attackers hijack the AI agent by abusing the exte...

VulnerabilityAI SecurityLLM Security
Read More → Use Tool →
2026-05-07Dark Reading
TrustFall Flaw Exposes Code Execution in Claude, Cursor, Gemini, CoPilot

Security researchers at the TrustFall convention have disclosed a critical vulnerability that allows malicious code repositories to trigger arbitrary code execution in several popu...

VulnerabilitySupply ChainLLM Security
Read More → Use Tool →
2026-05-06The Hacker News
AI Agents Outpacing Enterprise Governance: Security Teams Sound Alarm

According to Gartner's inaugural Market Guide for Guardian Agents, published in 2024, enterprise deployment of AI agents is accelerating at a pace that outstrips the development of...

AI SecurityAI ThreatsLLM Security
Read More → Use Tool →
2026-05-01Dark Reading
Why AI Integrations Are Deleting Production Databases

The rapid adoption of AI agents in production environments has uncovered a troubling trend: systems that are supposed to enhance operational efficiency are instead causing catastro...

AI SecurityLLM SecurityVulnerability
Read More → Use Tool →
2026-04-30Dark Reading
Anthropic's Mythos AI Redefines Cyber Threat Landscape

Anthropic has officially launched Mythos, its latest large language model designed with a reported 1.2 trillion parameters and native multimodal reasoning capabilities. According t...

AI SecurityAI ThreatsLLM Security
Read More → Use Tool →
2026-04-30Dark Reading
Japan Banks on Edge Over Anthropic's Superhacker AI Model

Japan’s financial services industry is on high alert after the release of Anthropic’s latest large language model, internally dubbed “Claude Mythos,” which early demonstrations sug...

AI SecurityAI ThreatsLLM Security
Read More → Use Tool →
2026-04-30The Hacker News
Google Patches Critical Gemini CLI Flaw Enabling Remote Code Execution

Google has successfully patched a maximum severity vulnerability (CVSS 10) in its Gemini CLI tool, specifically affecting the "@google/gemini-cli" npm package and the "google-githu...

VulnerabilitySupply ChainLLM Security
Read More → Use Tool →
2026-04-29The Hacker News
Critical LiteLLM SQL Injection CVE-2026-42208 Exploited Within 36 Hours

Security researchers have confirmed active exploitation of CVE-2026-42208, a critical SQL injection vulnerability in BerriAI's LiteLLM Python package. The flaw, which was disclosed...

Zero-DayVulnerabilityLLM Security
Read More → Use Tool →
2026-04-27Dark Reading
Frontier AI Models Spark Cybersecurity Debate Among Experts

The rapid advancement of frontier large language models, including Anthropic's Claude family and OpenAI's rumored GPT-5.5, has ignited fierce debate within the cybersecurity commun...

AI SecurityLLM SecurityAI Threats
Read More → Use Tool →
2026-04-27The Hacker News
Mythos AI Transforms Vulnerability Discovery, Remediation Gap Widens

Anthropic on April 7 released the public preview of Claude Mythos, a cybersecurity‑focused large language model built on the company’s latest transformer stack. The model ships wit...

VulnerabilityAI SecurityLLM Security
Read More → Use Tool →
2026-04-24The Hacker News
Bridging AI Agent Authority Gaps: Continuous Observability for Enterprise Security

Enterprise organizations deploying AI agents are confronting a critical security gap that traditional governance frameworks fail to address: the AI Agent Authority Gap. As autonomo...

AI SecurityLLM Security
Read More → Use Tool →
2026-04-24The Hacker News
LMDeploy CVE-2026-33626 Flaw Active Exploitation After 13 Hours

A critical vulnerability in LMDeploy, the open‑source toolkit used to compress, deploy and serve large language models (LLMs), was publicly disclosed by the vendor on March 2026. T...

Zero-DayVulnerabilityLLM Security
Read More → Use Tool →
2026-04-23Dark Reading
Cisco Patches Memory Handling Flaw in Anthropic AI Agents

Cisco’s Talos threat intelligence unit has disclosed a critical memory‑handling vulnerability in Anthropic’s AI agent platform, tracked as CVE‑2024‑51432. The flaw resides in the m...

VulnerabilityAI SecurityLLM Security
Read More → Use Tool →
2026-04-23The Hacker News
Anthropic Delays Project Glasswing AI Vulnerability Finder Public Release

Anthropic has announced Project Glasswing, an AI model designed to discover software vulnerabilities with unprecedented effectiveness. The company has taken the extraordinary step ...

AI SecurityVulnerabilityLLM Security
Read More → Use Tool →
2026-04-21Ars Technica
Mozilla Finds 271 Firefox 150 Vulnerabilities Using Anthropic's Mythos AI

Mozilla has identified 271 security vulnerabilities in Firefox 150 using Anthropic's Mythos large language model, marking a significant milestone in AI-assisted code analysis. The ...

VulnerabilityAI SecurityLLM Security
Read More → Use Tool →