1258 matches found
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...
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...
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...
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...
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...
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...
Mattermost doesn't restrict domains LLM can request to contact upstream
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...
GHSA-9H6J-4FFX-CM84 Mattermost doesn't restrict domains LLM can request to contact upstream
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...
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...
CVE-2025-31363
Mattermost CVE-2025-31363 affects Mattermost Server in versions 10.4.x <= 10.4.2, 10.5.x <= 10.5.0, and 9.11.x
CVE-2025-31363 Data exfiltration via AI plugin Jira tool
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...
CVE-2025-31363 Data exfiltration via AI plugin Jira tool
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...
Bypassing Prompt Injection and Jailbreak Detection in LLM Guardrails
Large Language Models LLMs guardrail systems are designed to protect against prompt injection and jailbreak attacks. However, they remain vulnerable to evasion techniques. We demonstrate two approaches for bypassing LLM prompt injection and jailbreak detection systems via traditional character...
Mattermost 安全漏洞
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...
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...