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...

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...

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...

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...

GTSD: Generative Text Steganography Based on Diffusion Model

With the rapid development of deep learning, existing generative text steganography methods based on autoregressive models have achieved success. However, these autoregressive steganography approaches have certain limitations. Firstly, existing methods require encoding candidate words according t...

CVE-2025-31363

Mattermost versions 10.4.x = 10.4.2, 10.5.x = 10.5.0, 9.11.x = 9.11.9 fail to restrict domains the LLM can request to contact upstream which allows an authenticated user to exfiltrate data from an arbitrary server accessible to the victim via performing a prompt injection in the AI plugin's Jira...

T2VShield: Model-Agnostic Jailbreak Defense for Text-To-Video Models

The rapid development of generative artificial intelligence has made text to video models essential for building future multimodal world simulators. However, these models remain vulnerable to jailbreak attacks, where specially crafted prompts bypass safety mechanisms and lead to the generation of...

Adversarial Attacks on LLM-As-A-Judge Systems: Insights from Prompt Injections

LLM as judge systems used to assess text quality code correctness and argument strength are vulnerable to prompt injection attacks. We introduce a framework that separates content author attacks from system prompt attacks and evaluate five models Gemma 3.27B Gemma 3.4B Llama 3.2 3B GPT 4 and Clau...

PICO: Secure Transformers Via Robust Prompt Isolation and Cybersecurity Oversight

We propose a robust transformer architecture designed to prevent prompt injection attacks and ensure secure, reliable response generation. Our PICO Prompt Isolation and Cybersecurity Oversight framework structurally separates trusted system instructions from untrusted user inputs through dual...

Mattermost Information Disclosure Vulnerability

Mattermost is an open source collaboration platform from Mattermost, Inc. in the United States. Mattermost suffers from an information disclosure vulnerability. The vulnerability stems from an under-restricted LLM request domain. An attacker can exploit the vulnerability to perform prompt injecti...

Prompt Injection

github.com/mattermost/mattermost-server is vulnerable to prompt injection. The vulnerability is due to insufficient domain restriction to the AI plugin's Jira tool, allowing authenticated users to exfiltrate data from arbitrary servers via crafted prompts...

Mattermost Server 9.11.x < 9.11.10 / 10.4.x < 10.4.3 / 10.5.x < 10.5.1 / 10.6.0 (MMSA-2024-00401)

The version of Mattermost Server installed on the remote host is prior to 9.11.10, 10.4.3, or 10.5.1 / 10.6.0. It is, therefore, affected by a vulnerability as referenced in the MMSA-2024-00401 advisory. - Mattermost versions 10.4.x = 10.4.2, 10.5.x = 10.5.0, 9.11.x = 9.11.9 fail to restrict...

Malware in cantina-senior-frontend-interview-prompt

Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be rotated immediately from a different computer. The package should be removed, but as full control of the computer may have been given to an outsid...

Amplified Vulnerabilities: Structured Jailbreak Attacks on LLM-Based Multi-Agent Debate

Multi-Agent Debate MAD, leveraging collaborative interactions among Large Language Models LLMs, aim to enhance reasoning capabilities in complex tasks. However, the security implications of their iterative dialogues and role-playing characteristics, particularly susceptibility to jailbreak attack...