LeechHijack: Covert Computational Resource Exploitation in Intelligent Agent Systems

Large Language Model LLM-based agents have demonstrated remarkable capabilities in reasoning, planning, and tool usage. The recently proposed Model Context Protocol MCP has emerged as a unifying framework for integrating external tools into agent systems, enabling a thriving open ecosystem of...

ADSLR NBR1005GPEV2 命令注入漏洞

The ADSLR NBR1005GPEV2 is a wireless router from China's Flying Fish Star ADSLR. A command injection vulnerability exists in the ADSLR NBR1005GPEV2 version 250814-r037c, which stems from the incorrect operation of the parameter mac in the file /sendorder.cgi, which could lead to command injection...

MCP Watch 操作系统命令注入漏洞

MCP Watch is a comprehensive security scanning program for Model Context Protocol servers by the individual developer Kapil Duraphe. An operating system command injection vulnerability exists in MCP Watch version 0.1.2 and earlier, which stems from command injection and could lead to arbitrary...

ASB-A-443742829

In setDisplayName of AssociationRequest.java, there is a possible way to cause CDM associations to persist after the user has disassociated them due to improper input validation. This could lead to local escalation of privilege with no additional execution privileges needed. User interaction is n...

PT-2025-48575

Name of the Vulnerable Software and Affected Versions MCP Watch versions 0.1.2 and earlier Description MCP Watch, a security scanner for Model Context Protocol MCP servers, contains a Command Injection issue in the cloneRepo method of the MCPScanner class. The application directly passes the...

Demystifying Feature Engineering in Malware Analysis of API Call Sequences

Machine learning ML has been widely used to analyze API call sequences in malware analysis, which typically requires the expertise of domain specialists to extract relevant features from raw data. The extracted features play a critical role in malware analysis. Traditional feature extraction is...

PT-2025-48589

Name of the Vulnerable Software and Affected Versions Tencent MedicalNet affected versions not specified Description A flaw exists within the generate model function that allows remote attackers to execute arbitrary code on affected installations of Tencent MedicalNet. The issue stems from...

PT-2025-48471

Name of the Vulnerable Software and Affected Versions Socomec DIRIS Digiware M-70 version 1.6.9 Description A denial of service condition can occur in the Modbus TCP functionality. Sending a crafted network packet can cause a denial of service and potentially reset credentials to default document...

Securing Large Language Models (LLMs) from Prompt Injection Attacks

Large Language Models LLMs are increasingly being deployed in real-world applications, but their flexibility exposes them to prompt injection attacks. These attacks leverage the model's instruction-following ability to make it perform malicious tasks. Recent work has proposed JATMO, a task-specif...

EUVD-2025-199932

A vulnerability was found in ZenTao up to 21.7.6-8564. This affects the function makeRequest of the file module/ai/model.php. The manipulation of the argument Base results in server-side request forgery. The attack can be launched remotely. The exploit has been made public and could be used...

CVE-2025-13789

ZenTao up to 21.7.6-8564 is affected by a vulnerability in the makeRequest function of module/ai/model.php where improper handling of the Base parameter enables server-side request forgery (SSRF). The issue is exploitable remotely, and public exploits have been reported. Upgrading to version 21.7...

Malicious code in chat-prompt-logger (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 f25a736985f5c0bb50156fdc7de61e976b16416f42c44a2682b5ce718401383b The package provides a logger of LLM prompts that at the same time looks for hidden instructions and executes them. --- Category: MALICIOUS - The campaign has...

PT-2025-48391

Name of the Vulnerable Software and Affected Versions ZenTao versions up to 21.7.6-8564 Description A server-side request forgery condition exists in ZenTao. The issue is related to the makeRequest function within the module/ai/model.php file. Manipulation of the Base argument can trigger the...

Nature Easy Soft Network Technology ZenTao 代码问题漏洞

Nature Easy Soft Network Technology ZenTao is a set of open source project management software from China's Nature Easy Soft Network Technology Nature Easy Soft Network Technology. The software includes product management, project management, quality management and document management functions. ...

Prompt Injection Through Poetry

In a new paper, "Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models," researchers found that turning LLM prompts into poetry resulted in jailbreaking the models: Abstract : We present evidence that adversarial poetry functions as a universal single-turn...

Evaluating LLMs for One-Shot Patching of Real and Artificial Vulnerabilities

Automated vulnerability patching is crucial for software security, and recent advancements in Large Language Models LLMs present promising capabilities for automating this task. However, existing research has primarily assessed LLMs using publicly disclosed vulnerabilities, leaving their...

Incorrect Implementation of Authentication Algorithm

Overview Affected versions of this package are vulnerable to Incorrect Implementation of Authentication Algorithm. An attacker can gain unauthorized access to another user's account by leveraging a specially crafted email address when switching authentication methods and sending a request to the...

An Efficient Privacy-Preserving Intrusion Detection Scheme for UAV Swarm Networks

The rapid proliferation of unmanned aerial vehicles UAVs and their applications in diverse domains, such as surveillance, disaster management, agriculture, and defense, have revolutionized modern technology. While the potential benefits of swarm-based UAV networks are growing significantly, they...

Remote Command Execution

scio-pypi is vulnerable to Remote Command Execution. The vulnerability is due to torch.load executing unsafe deserialization even when weightsonly=True, which allows an attacker to craft malicious model files that trigger arbitrary code execution during loading...

CVE-2025-13735

Out-of-bounds Read vulnerability in ASR1903、ASR3901 in ASR LapwingLinux on Linux nrfw modules. This vulnerability is associated with program files Code/nrfw/DLP/src/NrCgi.C. This issue affects LapwingLinux: before 2025/11/26...