Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration

Memory systems enable otherwise-stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. We characterize the Trojan Hippo attack, a class of persistent memory attacks that operates in a more realistic threat model than prior memory poisoning work:...

Intellicise Wireless Networks Meet Agentic AI: A Security and Privacy Perspective

Intellicise Intelligent and Concise wireless network is the main direction of the evolution of future mobile communication systems, a perspective now widely acknowledged across academia and industry. As a key technology within it, Agentic AI has garnered growing attention due to its advanced...

PT-2026-1688

Name of the Vulnerable Software and Affected Versions affected versions not specified Description Attackers are leveraging artificial intelligence to customize malicious payloads in phishing campaigns, enabling them to circumvent security defenses. This issue is related to email security protocol...

Toward Understanding Security Issues in the Model Context Protocol Ecosystem

The Model Context Protocol MCP is an emerging open standard that enables AI-powered applications to interact with external tools through structured metadata. A rapidly growing ecosystem has formed around MCP, including a wide range of MCP hosts i.e., Cursor, Windsurf, Claude Desktop, and Cline, M...

Exploiting Web Search Tools of AI Agents for Data Exfiltration

Large language models LLMs are now routinely used to autonomously execute complex tasks, from natural language processing to dynamic workflows like web searches. The usage of tool-calling and Retrieval Augmented Generation RAG allows LLMs to process and retrieve sensitive corporate data, amplifyi...

Scattered Spider Hacker Arrests Halt Attacks, But Copycat Threats Sustain Security Pressure

Google Cloud's Mandiant Consulting has revealed that it has witnessed a drop in activity from the notorious Scattered Spider group, but emphasized the need for organizations to take advantage of the lull to shore up their defenses. "Since the recent arrests tied to the alleged Scattered Spider...

Revisiting UNC3886 Tactics to Defend Against Present Risk

We examine the past tactics used by UNC3886 to gain insight on how to best strengthen defenses against the ongoing and emerging threats of this APT group...

Preventing Zero-Click AI Threats: Insights from EchoLeak

A zero-click exploit called EchoLeak reveals how AI assistants like Microsoft 365 Copilot can be manipulated to leak sensitive data without user interaction. This entry breaks down how the attack works, why it matters, and what defenses are available to proactively mitigate this emerging AI-nativ...

Inside LockBit: Defense Lessons from the Leaked LockBit Negotiations

The LockBit ransomware gang recently suffered a significant data breach. Their dark web affiliate panels were defaced with the message "Don't do crime CRIME IS BAD xoxo from Prague," linking to a MySQL database dump. This archive contains a SQL file from LockBit's affiliate panel database that...

Security Vulnerabilities in Quantum Cloud Systems: a Survey on Emerging Threats

Quantum computing is becoming increasingly widespread due to the potential and capabilities to solve complex problems beyond the scope of classical computers. As Quantum Cloud services are adopted by businesses and research groups, they allow for greater progress and application in many fields...

U.S. Telecom Giant T-Mobile Detects Network Intrusion Attempts from Wireline Provider

U.S. telecom service provider T-Mobile said it recently detected attempts made by bad actors to infiltrate its systems in recent weeks but noted that no sensitive data was accessed. These intrusion attempts "originated from a wireline provider's network that was connected to ours," Jeff Simon,...

Supply Chain Attacks Can Exploit Entry Points in Python, npm, and Open-Source Ecosystems

Cybersecurity researchers have found that entry points could be abused across multiple programming ecosystems like PyPI, npm, Ruby Gems, NuGet, Dart Pub, and Rust Crates to stage software supply chain attacks. "Attackers can leverage these entry points to execute malicious code when specific...

Microsoft Detects Growing Use of File Hosting Services in Business Email Compromise Attacks

Microsoft is warning of cyber attack campaigns that abuse legitimate file hosting services such as SharePoint, OneDrive, and Dropbox that are widely used in enterprise environments as a defense evasion tactic. The end goal of the campaigns are broad and varied, allowing threat actors to compromis...

Rapid7 Introduces Vector Command, a New Managed Service for Continuous Red Teaming

Rapid7 is delighted to announce the launch of Vector Command, a continuous red teaming managed service designed to assess your external attack surface and identify gaps in the security defenses on an ongoing basis. Following the launch of Surface Command and Exposure Command in August, Vector...

New Attack Technique Exploits Microsoft Management Console Files

Threat actors are exploiting a novel attack technique in the wild that leverages specially crafted management saved console MSC files to gain full code execution using Microsoft Management Console MMC and evade security defenses. Elastic Security Labs has codenamed the approach GrimResource after...

RHEL 7 : CloudForms 4.6.6 (RHSA-2018:3816)

The remote Redhat Enterprise Linux 7 host has packages installed that are affected by multiple vulnerabilities as referenced in the RHSA-2018:3816 advisory. Red Hat CloudForms Management Engine delivers the insight, control, and automation needed to address the challenges of managing virtual...

Researchers Highlight Google's Gemini AI Susceptibility to LLM Threats

Google's Gemini large language model LLM is susceptible to security threats that could cause it to divulge system prompts, generate harmful content, and carry out indirect injection attacks. The findings come from HiddenLayer, which said the issues impact consumers using Gemini Advanced with Goog...

Ransomware-as-a-Service: The Growing Threat You Can't Ignore

Ransomware attacks have become a significant and pervasive threat in the ever-evolving realm of cybersecurity. Among the various iterations of ransomware, one trend that has gained prominence is Ransomware-as-a-Service RaaS. This alarming development has transformed the cybercrime landscape,...

New BLISTER Malware Using Code Signing Certificates to Evade Detection

Cybersecurity researchers have disclosed details of an evasive malware campaign that makes use of valid code signing certificates to sneak past security defenses and stay under the radar with the goal of deploying Cobalt Strike and BitRAT payloads on compromised systems. The binary, a loader, has...

Detecting Credential Stealing Attacks Through Active In-Network Defense

ARCHIVED STORY Detecting Credential Stealing Attacks Through Active In-Network Defense By Trellix · September 22, 2021 This blog was written by Chintan Shah Executive Summary Today, enterprises tend to use multiple layers of security defenses, ranging from perimeter defense on network entry point...