Configure Audit Rules for Network Environment

Attackers may change the system domain name and host name to launch attacks, such as host spoofing. It is recommended that the user set the audit of system calls setdomainname and sethostname and the audit of the /etc/hosts file to monitor changes in the system domain name and host name. You can...

LlamaFirewall: an Open Source Guardrail System for Building Secure AI Agents

Large language models LLMs have evolved from simple chatbots into autonomous agents capable of performing complex tasks such as editing production code, orchestrating workflows, and taking higher-stakes actions based on untrusted inputs like webpages and emails. These capabilities introduce new...

The vulnerability of the PCMan FTP Server relates to the occurrence of operations beyond the buffer boundaries in memory. This allows attackers to compromise the confidentiality, integrity, and accessibility of the protected information.

The vulnerability of the PCMan FTP Server relates to the execution of operations beyond the buffer boundaries in memory when processing the prompt parameter. Exploiting this vulnerability allows a remote attacker to compromise the confidentiality, integrity, and accessibility of the protected...

CVE-2025-4158

A vulnerability was found in PCMan FTP Server up to 2.0.7. It has been classified as critical. Affected is an unknown function of the component PROMPT Command Handler. The manipulation leads to buffer overflow. It is possible to launch the attack remotely. The exploit has been disclosed to the...

CVE-2025-4158

A vulnerability was found in PCMan FTP Server up to 2.0.7. It has been classified as critical. Affected is an unknown function of the component PROMPT Command Handler. The manipulation leads to buffer overflow. It is possible to launch the attack remotely. The exploit has been disclosed to the...

CVE-2025-4158 PCMan FTP Server PROMPT Command buffer overflow

A vulnerability was found in PCMan FTP Server up to 2.0.7. It has been classified as critical. Affected is an unknown function of the component PROMPT Command Handler. The manipulation leads to buffer overflow. It is possible to launch the attack remotely. The exploit has been disclosed to the...

CVE-2025-4158

CVE-2025-4158 affects PCMan FTP Server versions 2.0.0–2.0.7, with a buffer overflow in the PROMPT Command Handler caused by insufficient input length validation. This enables remote exploitation; public exploits/ PoCs are noted in sources. Connected documents confirm the issue in multiple advisor...

CVE-2025-4158: Buffer Copy without Checking Size of Input

A vulnerability was found in PCMan FTP Server up to 2.0.7. It has been classified as critical. Affected is an unknown function of the component PROMPT Command Handler. The manipulation leads to buffer overflow. It is possible to launch the attack remotely. The exploit has been disclosed to the...

OET: Optimization-Based Prompt Injection Evaluation Toolkit

Large Language Models LLMs have demonstrated remarkable capabilities in natural language understanding and generation, enabling their widespread adoption across various domains. However, their susceptibility to prompt injection attacks poses significant security risks, as adversarial inputs can...

PCMan FTP Server 安全漏洞

PCMan FTP Server is PCMan open source set of FTP server software. PCMan FTP Server suffers from a buffer overflow vulnerability that originates from the PROMPT command handler failing to properly validate the length of input data, which can be exploited by an attacker to cause a denial of service...

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...

LASHED: LLMs and Static Hardware Analysis for Early Detection of RTL Bugs

While static analysis is useful in detecting early-stage hardware security bugs, its efficacy is limited because it requires information to form checks and is often unable to explain the security impact of a detected vulnerability. Large Language Models can be useful in filling these gaps by...

Traceback of Poisoning Attacks to Retrieval-Augmented Generation

Large language models LLMs integrated with retrieval-augmented generation RAG systems improve accuracy by leveraging external knowledge sources. However, recent research has revealed RAG's susceptibility to poisoning attacks, where the attacker injects poisoned texts into the knowledge database,...

New Reports Uncover Jailbreaks, Unsafe Code, and Data Theft Risks in Leading AI Systems

Various generative artificial intelligence GenAI services have been found vulnerable to two types of jailbreak attacks that make it possible to produce illicit or dangerous content. The first of the two techniques, codenamed Inception, instructs an AI tool to imagine a fictitious scenario, which...

Akamai Firewall for AI: Get Powerful Protection for New LLM App Threats

Protect against LLM attacks such as prompt injection, exfiltration and extraction, and toxic AI outputs with Akamai Firewall for AI...

Applying Security Engineering to Prompt Injection Security

This seems like an important advance in LLM security against prompt injection: Google DeepMind has unveiled CaMeL CApabilities for MachinE Learning, a new approach to stopping prompt-injection attacks that abandons the failed strategy of having AI models police themselves. Instead, CaMeL treats...

Token-Efficient Prompt Injection Attack: Provoking Cessation in LLM Reasoning Via Adaptive Token Compression

While reasoning large language models LLMs demonstrate remarkable performance across various tasks, they also contain notable security vulnerabilities. Recent research has uncovered a "thinking-stopped" vulnerability in DeepSeek-R1, where model-generated reasoning tokens can forcibly interrupt th...

SecRepoBench: Benchmarking LLMs for Secure Code Generation in Real-World Repositories

This paper introduces SecRepoBench, a benchmark to evaluate LLMs on secure code generation in real-world repositories. SecRepoBench has 318 code generation tasks in 27 C/C++ repositories, covering 15 CWEs. We evaluate 19 state-of-the-art LLMs using our benchmark and find that the models struggle...

CachePrune: Neural-Based Attribution Defense against Indirect Prompt Injection Attacks

Large Language Models LLMs are identified as being susceptible to indirect prompt injection attack, where the model undesirably deviates from user-provided instructions by executing tasks injected in the prompt context. This vulnerability stems from LLMs' inability to distinguish between data and...

Robustness Via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction

Large language models LLMs have demonstrated impressive performance and have come to dominate the field of natural language processing NLP across various tasks. However, due to their strong instruction-following capabilities and inability to distinguish between instructions and data content, LLMs...