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

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...

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...

PT-2025-16572

Name of the Vulnerable Software and Affected Versions Mattermost versions 9.11.x through 9.11.9 Mattermost versions 10.4.x through 10.4.2 Mattermost versions 10.5.x through 10.5.0 Description The issue allows an authenticated user to exfiltrate data from an arbitrary server accessible to the vict...

InjectLab: a Tactical Framework for Adversarial Threat Modeling against Large Language Models

Large Language Models LLMs are changing the way people interact with technology. Tools like ChatGPT and Claude AI are now common in business, research, and everyday life. But with that growth comes new risks, especially prompt-based attacks that exploit how these models process language. InjectLa...

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...

CVE-2025-31363: Improper Validation of Generative AI Output

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 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-2025-3578

A malicious, authenticated user in Aidex, versions prior to 1.7, could list credentials of other users, create or modify existing users in the application, list credentials of users in production or development environments. In addition, it would be possible to cause bugs that would result in the...

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...

CVE-2025-3579

Aidex CVE-2025-3579 affects versions prior to 1.7. The issue is a prompt-injection vulnerability in the /api//message endpoint where the content parameter can be manipulated by an authenticated user with access to an open registry, enabling execution of OS commands (Unix), interaction with intern...

CVE-2025-3579 Code Injection Vulnerability in AiDex

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...

CVE-2025-3578 Adversarial Input Handling Vulnerability in AiDex

A malicious, authenticated user in Aidex, versions prior to 1.7, could list credentials of other users, create or modify existing users in the application, list credentials of users in production or development environments. In addition, it would be possible to cause bugs that would result in the...

CVE-2025-3578 Adversarial Input Handling Vulnerability in AiDex

A malicious, authenticated user in Aidex, versions prior to 1.7, could list credentials of other users, create or modify existing users in the application, list credentials of users in production or development environments. In addition, it would be possible to cause bugs that would result in the...

PT-2025-16308 · Laravel +4 · Laravel +4

Name of the Vulnerable Software and Affected Versions: Aidex versions prior to 1.7 Description: The issue allows an authenticated malicious user to execute unauthorized commands within the system by exploiting an open registry. This can include executing operating system commands, interacting wit...

PT-2025-16307 · Aidex · Aidex

Name of the Vulnerable Software and Affected Versions: Aidex versions prior to 1.7 Description: A malicious, authenticated user could list credentials of other users, create or modify existing users in the application, list credentials of users in production or development environments, and cause...

CVE-2025-3579: Improper Control of Generation of Code

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...

Token-Level Constraint Boundary Search for Jailbreaking Text-To-Image Models

Recent advancements in Text-to-Image T2I generation have significantly enhanced the realism and creativity of generated images. However, such powerful generative capabilities pose risks related to the production of inappropriate or harmful content. Existing defense mechanisms, including prompt...

R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning

Vision-language models VLMs, such as CLIP, have gained significant popularity as foundation models, with numerous fine-tuning methods developed to enhance performance on downstream tasks. However, due to their inherent vulnerability and the common practice of selecting from a limited set of...