'CursorJack’ Attack Path Exposes Code Execution Risk in AI Development Environment
CursorJack shows how malicious MCP deeplinks in Cursor IDE can trigger user-approved code execution
20 articles
CursorJack shows how malicious MCP deeplinks in Cursor IDE can trigger user-approved code execution
Key Takeaways Introduction Application security is entering a new phase. It is now an AI problem, an API problem, and a runtime risk problem.
Explore key cybersecurity requirements and implementation deadlines for electric power utilities included in the NERC CIP-003-9 standard for Low-Impact BES (...
View CSAF Summary 3. TECHNICAL DETAILS The following versions of CODESYS in Festo Automation Suite are affected: FESTO Software Festo Automation Suite (versi...
The cybersecurity channel is evolving fast. Buying behaviors are shifting and customers are rethinking how they evaluate solutions.
A majority of security leaders are struggling to defend AI systems with tools and skills that are not fit for the challenge, according to the AI and Adversar...
Akamai says 87% of organizations suffered an API-related security incident last year
The US Cyber Monitoring Center should be operational in 2027, said the UK CMC leadership
An expensive mistake: Someone jumped at the opportunity to steal $4.4 million in crypto assets after South Korea’s National Tax Service exposed publicly the ...
Unit 42 research unveils LLM guardrail fragility using genetic algorithm-inspired prompt fuzzing. Discover scalable evasion methods and critical GenAI securi...
TELUS Digital has fallen victim to a security incident in which unsanctioned actors accessed its systems. Upon learning of this incident, the company said it...
Open source intelligence (OSINT) still sits outside the intelligence mainstream. If you’re not acquainted with the intelligence profession, you might not hav...
Go from zero to a fully populated Elastic Security environment without leaving your IDE, using open source Agent Skills.
Cloudflare is appealing a €14 million fine from Italian regulators over "Piracy Shield," a system that forces providers to block content without oversight. W...
Drivers in the Russian city of Perm have been enjoying an unexpected bonus this week: free parking. Not because the city council suddenly decided to embrace ...
As organizations adopt AI, security and governance remain core primitives for safe AI transformation and acceleration. The post New Microsoft Purview innovat...
For the latest discoveries in cyber research for the week of 16th March, please download our Threat Intelligence Bulletin. TOP ATTACKS AND BREACHES United St...
DNS-based attack in AWS Bedrock AgentCore lets AI sandboxes exfiltrate cloud data
An issue with the Companies House website has put the personal and corporate information of millions at risk
I’m skeptical about—and not qualified to review—this new result in factorization with a quantum computer, but if it’s true it’s a theoretical improvement in ...