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...

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-2025-3579

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...

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...

Brave Software: Prompt Injection via GitHub Patch in Brave AI Chat (Leo)

Component: Brave AI Chat brave-core/components/aichat/ Severity: High Confirmed ability to override AI instructions and persona via fetched content Vulnerability Summary The Brave AI Chat feature allows fetching .patch files from GitHub pull request pages to use as context. A combination of...

CVE-2025-32018 Arbitrary file write from Cursor Agent through a prompt injection from malicious @Docs

Cursor is a code editor built for programming with AI. In versions 0.45.0 through 0.48.6, the Cursor app introduced a regression affecting the set of file paths the Cursor Agent is permitted to modify automatically. Under specific conditions, the agent could be prompted, either directly by the us...

CVE-2025-32018 Arbitrary file write from Cursor Agent through a prompt injection from malicious @Docs

Cursor is a code editor built for programming with AI. In versions 0.45.0 through 0.48.6, the Cursor app introduced a regression affecting the set of file paths the Cursor Agent is permitted to modify automatically. Under specific conditions, the agent could be prompted, either directly by the us...

CVE-2025-32018 Arbitrary file write from Cursor Agent through a prompt injection from malicious @Docs

Cursor is a code editor built for programming with AI. In versions 0.45.0 through 0.48.6, the Cursor app introduced a regression affecting the set of file paths the Cursor Agent is permitted to modify automatically. Under specific conditions, the agent could be prompted, either directly by the us...

Gitlab -- Vulnerabilities

Gitlab reports: Cross-site Scripting XSS through merge-request error messages Cross-site Scripting XSS through improper rendering of certain file types Admin Privileges Persists After Role is Revoked External user can access internal projects Prompt injection in Amazon Q integration may allow...

CVE-2024-10950

In binary-husky/gptacademic version = 3.83, the plugin CodeInterpreter is vulnerable to code injection caused by prompt injection. The root cause is the execution of user-provided prompts that generate untrusted code without a sandbox, allowing the execution of parts of the LLM-generated code. Th...

GHSA-JMGM-GX32-VP4W LlamaIndex vulnerable to Creation of Temporary File in Directory with Insecure Permissions

A vulnerability in the defaultjsonalyzer function of the JSONalyzeQueryEngine in the run-llama/llamaindex repository allows for SQL injection via prompt injection. This can lead to arbitrary file creation and Denial-of-Service DoS attacks. The vulnerability affects the latest version and is fixed...

CVE-2024-10954 Prompt Injection Leading to RCE in binary-husky/gpt_academic Plugin `manim`

In the manim plugin of binary-husky/gptacademic, versions prior to the fix, a vulnerability exists due to improper handling of user-provided prompts. The root cause is the execution of untrusted code generated by the LLM without a proper sandbox. This allows an attacker to perform remote code...

CVE-2024-10954 Prompt Injection Leading to RCE in binary-husky/gpt_academic Plugin `manim`

In the manim plugin of binary-husky/gptacademic, versions prior to the fix, a vulnerability exists due to improper handling of user-provided prompts. The root cause is the execution of untrusted code generated by the LLM without a proper sandbox. This allows an attacker to perform remote code...

CVE-2024-10950 Code Injection in binary-husky/gpt_academic

In binary-husky/gptacademic version = 3.83, the plugin CodeInterpreter is vulnerable to code injection caused by prompt injection. The root cause is the execution of user-provided prompts that generate untrusted code without a sandbox, allowing the execution of parts of the LLM-generated code. Th...

CVE-2024-12911 SQL Injection in run-llama/llama_index

A vulnerability in the defaultjsonalyzer function of the JSONalyzeQueryEngine in the run-llama/llamaindex repository allows for SQL injection via prompt injection. This can lead to arbitrary file creation and Denial-of-Service DoS attacks. The vulnerability affects the latest version and is fixed...

Announcing the winners of the Adaptive Prompt Injection Challenge (LLMail-Inject)

We are excited to announce the winners of LLMail-Inject, our first Adaptive Prompt Injection Challenge! The challenge ran from December 2024 until February 2025 and was featured as one of the four official competitions of the 3rd IEEE Conference on Secure and Trustworthy Machine Learning IEEE...