Policy-Guided Threat Hunting: An LLM Enabled Framework with Splunk SOC Triage

With frequently evolving Advanced Persistent Threats APTs in cyberspace, traditional security solutions approaches have become inadequate for threat hunting for organizations. Moreover, SOC Security Operation Centers analysts are often overwhelmed and struggle to analyze the huge volume of logs...

PT-2026-28100

Name of the Vulnerable Software and Affected Versions Piwigo versions prior to 16.3.0 Description An issue exists where the ws std image sql filter function fails to perform escaping or type validation on four date filter parameters: f min date available, f max date available, f min date created,...

PT-2026-28101

Name of the Vulnerable Software and Affected Versions Coolify versions prior to 4.0.0-beta.464 Description An authorization bypass allows any authenticated user to access deployment details belonging to any team. The issue occurs because the GET /api/v1/deployments/uuid endpoint fails to use the...

PT-2026-28097

What are the limits of AI-assisted vulnerability hunting? I obtained 23 CVEs in one month. BentoML 8.2k CVE-2026-27905 HIGH SillyTavern 24.6k CVE-2026-26286 HIGH Plane 28.2k CVE-2026-27705 MEDIUM NocoDB 46.4k CVE-2026-28399 MEDIUM Mautic 8.4k CVE-2026-3105 HIGH File Browser 27.9k CVE-2026-28492...

Understanding Wiz’s Approach to Securing the AI Supply Chain

As organizations race to deploy AI, securing the rapidly expanding ecosystem of models, data, and dependencies has become a critical priority, much of which can be addressed by Wiz’s CNAPP solution...

API Security for AI Agents: Why Protection Has Never Been More Important.

For years, a lot of risky APIs survived simply because they were hard to find. They weren’t documented. Only a handful of engineers knew the endpoints. And if an attacker wanted to abuse them, they had to spend real time reverse‑engineering traffic and guessing how things worked. That “security b...

Echo-Mate 安全漏洞

Echo-Mate is a desktop robot and AI assistant developed by Kingham Xu. Previous versions of Echo-Mate, including V250329, had security vulnerabilities that stemmed from the reuse of released components after their disposal...

This Week in Spring - March 24th, 2026

Hi, Spring fans! Welcome to yet another rip-roarin' installment of This Week in Spring. As usual, we've got a ton to look into, so let's dive right in! Happy 22nd birthday to Spring Framework, released this day 22 years ago! and of course, next week, 1 April 2026, marks 12 years since Spring Boot...

SoK: The Attack Surface of Agentic AI -- Tools, and Autonomy

Recent AI systems combine large language models with tools, external knowledge via retrieval-augmented generation RAG, and even autonomous multi-agent decision loops. This agentic AI paradigm greatly expands capabilities - but also vastly enlarges the attack surface. In this systematization, we m...

NVIDIA Nemo Framework 代码问题漏洞

NVIDIA Nemo Framework is a framework developed by NVIDIA Corporation in the United States for building and deploying generative AI models. There are code-related vulnerabilities in the NVIDIA NeMo Framework, and attackers can exploit these vulnerabilities to trigger remote code execution...

CVE-2026-23481

Blinko is an AI-powered card note-taking project. Prior to version 1.8.4, there is an authenticated arbitrary file write vulnerability in saveAdditionalDevFile. This issue has been patched in version 1.8.4...

Introducing the Wiz Red Agent- AI-Powered Attacker

Red Agent is an AI-powered, context-aware attacker that uncovers complex exploitable risks across your entire attack surface, continuously and at scale...

Introducing Wiz Agents & Workflows: Security at the Speed of AI

A new security operating model powered by AI agents that removes bottlenecks and enables teams to act at the speed of AI...

ProHunter APT Hunting Tool / Paper

Advanced Persistent Threats APTs remain difficult to detect due to their stealthy nature and long-term persistence. To tackle this challenge, provenance-based threat hunting has gained traction as a proactive defense mechanism. This technique models audit logs as a whole-system provenance graph a...

FBI Warns Russian Hackers Target Signal, WhatsApp in Mass Phishing Attacks

Threat actors affiliated with Russian Intelligence Services are conducting phishing campaigns to compromise commercial messaging applications CMAs like WhatsApp and Signal to seize control of accounts belonging to individuals with high intelligence value, the U.S. Cybersecurity and Infrastructure...

Vanna 安全漏洞

Vanna is a personalized AI SQL proxy from Vanna Corporation. Versions of vanna 2.0.2 and earlier contained security vulnerabilities. These vulnerabilities stemmed from an injection vulnerability in the exec function located in the src/vanna/legacy directory, which could allow for remote execution...

Malicious code in mangrove-sdk (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 d6714958f20775c2347e9c8b606d1de2e28ed29fe4b1a82261ca4fb966fc20fa During installation, package attempts to modify LLM configuration files to provide a backdoor instruction for further control over an AI agent. --- Category:...

MAL-2026-2005 Malicious code in efghr-honeybee-sdk (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 e77e2d0088390e5dc421f70a65ade331bfbf554afcc9cc42362098d0ed130692 During installation, package attempts to modify LLM configuration files to provide a backdoor instruction for further control over an AI agent. --- Category:...

AI Runtime Threat Detection: From Input to Real-World Impact

Understanding and detecting AI-driven behavior across model, workload, and cloud...

CTI-REALM: A new benchmark for end-to-end detection rule generation with AI agents

Excerpt: CTI-REALM is Microsoft’s open-source benchmark for evaluating AI agents on real-world detection engineering—turning cyber threat intelligence CTI into validated detections. Instead of measuring “CTI trivia,” CTI-REALM tests end-to-end workflows: reading threat reports, exploring telemetr...