24 matches found
Machine Learning-Based Detection of MCP Attacks
The Model Context Protocol MCP is a new and emerging technology that extends the functionality of large language models, improving workflows but also exposing users to a new attack surface. Several studies have highlighted related security flaws, but MCP attack detection remains underexplored. To...
MalTool: Malicious Tool Attacks on LLM Agents
In a malicious tool attack, an attacker uploads a malicious tool to a distribution platform; once a user installs the tool and the LLM agent selects it during task execution, the tool can compromise the user's security and privacy. Prior work primarily focuses on manipulating tool names and...
Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools
Large language model LLM agents have demonstrated remarkable capabilities in complex reasoning and decision-making by leveraging external tools. However, this tool-centric paradigm introduces a previously underexplored attack surface: adversaries can manipulate tool metadata -- such as names,...
Researchers Demonstrate How MCP Prompt Injection Can Be Used for Both Attack and Defense
As the field of artificial intelligence AI continues to evolve at a rapid pace, fresh research has found how techniques that render the Model Context Protocol MCP susceptible to prompt injection attacks could be used to develop security tooling or identify malicious tools, according to a new repo...
In Gaming Item Scams and How to Avoid Them?
The popularity of the TF2 gaming and trading scene attracts scammers with phishing, fake trades, and malicious tools.…...
Black Basta Ransomware: What You Need to Know
Overview Black Basta is a ransomware group operating as ransomware-as-a-service RaaS, first spotted in April 2022. It is known to use double extortion techniques where the group demands payment for the decryption and non-release of stolen data. Earlier versions of Black Basta share many...
SUSE CVE-2024-26811
In the Linux kernel, the following vulnerability has been resolved: ksmbd: validate payload size in ipc response If installing malicious ksmbd-tools, ksmbd.mountd can return invalid ipc response to ksmbd kernel server. ksmbd should validate payload size of ipc response from ksmbd.mountd to avoid...
UBUNTU-CVE-2024-26811
In the Linux kernel, the following vulnerability has been resolved: ksmbd: validate payload size in ipc response If installing malicious ksmbd-tools, ksmbd.mountd can return invalid ipc response to ksmbd kernel server. ksmbd should validate payload size of ipc response from ksmbd.mountd to avoid...
Thousands of Dark Web Posts Expose ChatGPT Abuse Plans
By Deeba Ahmed Cybercriminals are actively promoting the abuse of ChatGPT and similar chatbots, offering a range of malicious tools from malware to phishing kits. This is a post from HackRead.com Read the original post: Thousands of Dark Web Posts Expose ChatGPT Abuse Plans...
Researchers Unveil ToddyCat's New Set of Tools for Data Exfiltration
The advanced persistent threat APT actor known as ToddyCat has been linked to a new set of malicious tools that are designed for data exfiltration, offering a deeper insight into the hacking crew's tactics and capabilities. The findings come from Kaspersky, which first shed light on the adversary...
INTERPOL Dismantles Infamous ’16shop’ Phishing-as-a-Service Platform
By Waqas The cybercrime platform 16shop sold hacking tools and other malicious tools used to compromise more than 70,000 users in 43 countries. This is a post from HackRead.com Read the original post: INTERPOL Dismantles Infamous 16shop Phishing-as-a-Service Platform...
Arid Viper Hacking Group Using Upgraded Malware in Middle East Cyber Attacks
The threat actor known as Arid Viper has been observed using refreshed variants of its malware toolkit in its attacks targeting Palestinian entities since September 2022. Symantec, which is tracking the group under its insect-themed moniker Mantis, said the adversary is "going to great lengths to...
Experts Warn of 'Beep' - A New Evasive Malware That Can Fly Under the Radar
Cybersecurity researchers have unearthed a new piece of evasive malware dubbed Beep that's designed to fly under the radar and drop additional payloads onto a compromised host. "It seemed as if the authors of this malware were trying to implement as many anti-debugging and anti-VM anti-sandbox...
Researchers Detail Malicious Tools Used by Cyber Espionage Group Earth Aughisky
A new piece of research has detailed the increasingly sophisticated nature of the malware toolset employed by an advanced persistent threat APT group named Earth Aughisky. "Over the last decade, the group has continued to make adjustments in the tools and malware deployments on specific targets...
Can Business Cybersecurity Protection Outlay Offset Cybercrime Insurance?
What is cybercrime insurance? Business cybersecurity protection cybercrime insurance safeguards organizations from any financial losses relating to damage to or loss of information from, networks and IT systems. This may include reputation loss, the cost of business interruption, infringement of...
Man pleads guilty to selling WhatsApp hacking tool, Signal Jammers & StingRays
By Waqas Carlos Guerrero, a prominent businessman marketed and sold hacking tools, IMSI catchers, and other malicious tools to clients… This is a post from HackRead.com Read the original post: Man pleads guilty to selling WhatsApp hacking tool, Signal Jammers & StingRays...
Breaking down NOBELIUM’s latest early-stage toolset
As we reported in earlier blog posts, the threat actor NOBELIUM recently intensified an email-based attack that it has been operating and evolving since early 2021. We continue to monitor this active attack and intend to post additional details as they become available. In this blog, we highlight...
Denial Of Service (DoS)
github.com/containers/storage/commit is vulnerable to Denial Of Service DoS. The decompression functionality allows an attacker to crash the application by pulling in malicious tools that resembles podman or cri-o during container image pulls...
Publicly Available Tools Seen in Cyber Incidents Worldwide
Summary This report is a collaborative research effort by the cyber security authorities of five nations: Australia, Canada, New Zealand, the United Kingdom, and the United States.12345 In it we highlight the use of five publicly available tools, which have been used for malicious purposes in...
The face of tomorrow’s cybercrime: Deepfake ransomware explained
While many countries are beginning to ease up on their respective pandemic lock downs—which, in turn, also means that everyone will soon ease into a life that is not quite post-COVID-19—we find ourselves once more on the cusp of change, an outlook that makes some feel anxious and others hopeful...