SCGAgent: Recreating the Benefits of Reasoning Models for Secure Code Generation with Agentic Workflows

Large language models LLMs have seen widespread success in code generation tasks for different scenarios, both everyday and professional. However current LLMs, despite producing functional code, do not prioritize security and may generate code with exploitable vulnerabilities. In this work, we...

A Novel Zero-Trust Identity Framework for Agentic AI: Decentralized Authentication and Fine-Grained Access Control

Traditional Identity and Access Management IAM systems, primarily designed for human users or static machine identities via protocols such as OAuth, OpenID Connect OIDC, and SAML, prove fundamentally inadequate for the dynamic, interdependent, and often ephemeral nature of AI agents operating at...

Mapping the Future of AI Security

AI security is one of the most pressing challenges facing the world today. Artificial intelligence is extraordinarily powerful, and, especially considering the advent of Agentic AI, growing more so by the day. But it is for this reason that securing it is so important. AI handles massive amounts ...

Microsoft extends Zero Trust to secure the agentic workforce

Microsoft’s 2025 Work Trend Index Read more ↗ Agentic AI transformation is giving rise to the Frontier Firm—a new type of organization characterized by on-demand intelligence and a workforce where humans and agents work in tandem. According to Microsoft’s 2025 Work Trend Index, we expect every...

Using Agentic AI & Digital Twin for Cyber Resilience

Learn how Trend is combining agentic AI and digital twin to transform the way organizations protect themselves from cyber threats...

RedTeamLLM: an Agentic AI Framework for Offensive Security

From automated intrusion testing to discovery of zero-day attacks before software launch, agentic AI calls for great promises in security engineering. This strong capability is bound with a similar threat: the security and research community must build up its models before the approach is leverag...

Privacy for Agentic AI

Sooner or later, it's going to happen. AI systems will start acting as agents, doing things on our behalf with some degree of autonomy. I think it's worth thinking about the security of that now, while its still a nascent idea. In 2019, I joined Inrupt, a company that is commercializing Tim...

Google Introduces Agentic AI to Combat Cybersecurity Threats

Google enhances cybersecurity with Agentic AI, launching Unified Security to fight zero-day exploits, enterprise threats, and credential-based attacks.…...

The API Imperative: Securing Agentic AI and Beyond

We recently released The Rise of Agentic AI, our API ThreatStats report for Q1 2025, finding that evolving API threats are fueled by the rise of agentic AI systems, growing complexity in cloud-native infrastructure, and a surge in software supply chain risks, and uncovered patterns and actionable...

ARCeR: an Agentic RAG for the Automated Definition of Cyber Ranges

The growing and evolving landscape of cybersecurity threats necessitates the development of supporting tools and platforms that allow for the creation of realistic IT environments operating within virtual, controlled settings as Cyber Ranges CRs. CRs can be exploited for analyzing vulnerabilities...

Agentic AI in the SOC - Dawn of Autonomous Alert Triage

Security Operations Centers SOCs today face unprecedented alert volumes and increasingly sophisticated threats. Triaging and investigating these alerts are costly, cumbersome, and increases analyst fatigue, burnout, and attrition. While artificial intelligence has emerged as a go-to solution, the...

agentic-fleet (>=0.1.6 <=0.4.81), composio (=0.1.1) +37 more potentially affected by CVE-2024-8952 via composio-core (>=0.3.13 <=0.7.21)

composio-core PYPI version =0.3.13, =0.1.6, =0.7.1, =0.3.13, =0.3.17, =0.3.13, =0.3.13, =0.7.1, =0.5.26, =0.3.13, =0.3.13, =0.3.13, =0.3.24, =0.7.15, =0.3.13, =0.7.20 and more Source cves: CVE-2024-8952 Source advisory: SNYK:PYTHON-COMPOSIOCORE-9637813...

aact-openhands (>=0.0.4 <=0.0.5), aberoth-ephemeris (>=1.0.0 <=1.0.2) +580 more potentially affected by CVE-2024-6844 via flask-cors (>=1.1.2 <=5.0.1)

flask-cors PYPI version =1.1.2, =0.0.4, =1.0.0, =1.8.8, =1.1.4, =0.0.1, =0.0.1, =0.0.4, =0.0.13, =0.1.0, =0.1.1, =0.1.0, =1.1.0, =0.0.1, =0.0.18, =1.0.2, =1.3.0 and more Source cves: CVE-2024-6844 Source advisory: OSV:GHSA-8VGW-P6QM-5GR7...

New AI &#8220;agents&#8221; could hold people for ransom in 2025

A paradigm shift in technology is hurtling towards us, and it could change everything we know about cybersecurity. Uhh, again, that is. When ChatGPT was unveiled to the public in late 2022, security experts looked on with cautious optimism, excited about the new technology but concerned about its...

Building Effective Agents with Spring AI (Part 1)

In a recent research publication: Building effective agents, Anthropic shared valuable insights about building effective Large Language Model LLM agents. What makes this research particularly interesting is its emphasis on simplicity and composability over complex frameworks. Let's explore how...

This Week in Spring - January 21st, 2025

Hi, Spring fans! Welcome to another rip-roaring installment of This Week in Spring! It's time to dive into this week's wondrous roundup! Good news, everybody! Spring Cloud AWS 3.3.0 is available! A neat video on stored procedures in Spring A very interesting article on the flow diagrams for Sprin...

Agentic AI in SOCs: A Solution to SOAR's Unfulfilled Promises

Security Orchestration, Automation, and Response SOAR was introduced with the promise of revolutionizing Security Operations Centers SOCs through automation, reducing manual workloads and enhancing efficiency. However, despite three generations of technology and 10 years of advancements, SOAR...

AI Pulse: Sticker Shock, Rise of the Agents, Rogue AI

This issue of AI Pulse is all about agentic AI: what it is, how it works, and why security needs to be baked in from the start to prevent agentic AI systems from going rogue once they’re deployed...

agenta (>=0.14.1a0 <=0.14.7a1), agentic-devops (>=0.0.5 <=0.0.9) +69 more potentially affected by CVE-2024-5710 via litellm (>=0.1.400 <=1.40.13)

litellm PYPI version =0.1.400, =0.14.1a0, =0.0.5, =0.0.4, =0.2.0, =0.29.0, =0.1.5, =0.1.0, =0.1.0, =0.0.1, =0.114.0, =0.0.1, =0.6.3, =0.7.10 and more Source cves: CVE-2024-5710 Source advisory: OSV:GHSA-QQCV-VG9F-5RR3...

agenta (>=0.14.1a0 <=0.14.7a1), agentic-devops (>=0.0.5 <=0.0.9) +71 more potentially affected by CVE-2024-5751 via litellm (>=0.1.400 <=1.40.15)

litellm PYPI version =0.1.400, =0.14.1a0, =0.0.5, =0.0.4, =0.2.0, =0.29.0, =0.1.5, =0.1.0, =0.1.0, =0.0.1, =0.114.0, =0.0.1, =0.6.3, =0.7.10 and more Source cves: CVE-2024-5751 Source advisory: OSV:GHSA-GPPG-GQW8-WH9G...