vscode -- security feature bypass vulnerability

VSCode developers report: A security feature bypass vulnerability exists in VS Code 1.100.0 and earlier versions where a maliciously crafted URL could be considered trusted when it should not have due to how VS Code handled glob patterns in the trusted domains feature. When paired with the fetch...

Red Teaming the Mind of the Machine: a Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Large Language Models LLMs are increasingly integrated into consumer and enterprise applications. Despite their capabilities, they remain susceptible to adversarial attacks such as prompt injection and jailbreaks that override alignment safeguards. This paper provides a systematic investigation o...

Defending against Indirect Prompt Injection by Instruction Detection

The integration of Large Language Models LLMs with external sources is becoming increasingly common, with Retrieval-Augmented Generation RAG being a prominent example. However, this integration introduces vulnerabilities of Indirect Prompt Injection IPI attacks, where hidden instructions embedded...

A Proposal for Evaluating the Operational Risk for ChatBots Based on Large Language Models

The emergence of Generative AI Gen AI and Large Language Models LLMs has enabled more advanced chatbots capable of human-like interactions. However, these conversational agents introduce a broader set of operational risks that extend beyond traditional cybersecurity considerations. In this work, ...

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...

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...

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...

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...

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...

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...

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...

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...

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...

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...

Breaking the Prompt Wall (I): a Real-World Case Study of Attacking ChatGPT Via Lightweight Prompt Injection

Whitepaper called Breaking The Prompt Wall I: A Real-World Case Study Of Attacking ChatGPT Via Lightweight Prompt Injection...

CVE-2025-3579

In versions prior to Aidex 1.7, an authenticated malicious user, taking advantage of an open registry, could execute unauthorised commands within the system. This includes executing operating system Unix commands, interacting with internal services such as PHP or MySQL, and even invoking native...