1941 matches found
CVE-2025-66451
LibreChat is a ChatGPT clone with additional features. In versions 0.8.0 and below, when creating prompts, JSON requests are sent to define and modify the prompts via PATCH endpoint for prompt groups /api/prompts/groups/:groupId. However, the request bodies are not sufficiently validated for prop...
EUVD-2025-202929
LibreChat is a ChatGPT clone with additional features. In versions 0.8.0 and below, when creating prompts, JSON requests are sent to define and modify the prompts via PATCH endpoint for prompt groups /api/prompts/groups/:groupId. However, the request bodies are not sufficiently validated for prop...
PT-2025-50772
Name of the Vulnerable Software and Affected Versions LibreChat versions 0.8.0 and below Description LibreChat, a ChatGPT clone, has an issue where input validation is insufficient when creating prompts. JSON requests sent to the /api/prompts/groups/:groupId endpoint via the PATCH method are not...
LibreChat 安全漏洞
LibreChat is an enhanced ChatGPT clone by Danny Avila Personal Developer. A security vulnerability exists in LibreChat 0.8.0 and prior versions that stems from insufficient validation of JSON request input, which may result in unintended prompt modifications...
CVE-2025-67510 MySQLWriteTool allows arbitrary/destructive SQL when exposed to untrusted prompts (agent “footgun”)
Neuron is a PHP framework for creating and orchestrating AI Agents. In versions 2.8.11 and below, the MySQLWriteTool executes arbitrary SQL provided by the caller using PDO::prepare + execute without semantic restrictions. This is consistent with the name “write tool”, but in an LLM/agent context...
EUVD-2025-202170
Neuron is a PHP framework for creating and orchestrating AI Agents. In versions 2.8.11 and below, the MySQLWriteTool executes arbitrary SQL provided by the caller using PDO::prepare + execute without semantic restrictions. This is consistent with the name “write tool”, but in an LLM/agent context...
CVE-2025-67510
Neuron is a PHP framework for AI Agents. Versions 2.8.11 and earlier have a vulnerability in the MySQLWriteTool that can execute arbitrary SQL provided by the caller via PDO::prepare() and execute(), without semantic restrictions. In an LLM/agent context this enables prompt injection or indirect ...
GHSA-898V-775G-777C Neuron MySQLWriteTool allows arbitrary/destructive SQL when exposed to untrusted prompts (agent “footgun”)
Impact MySQLWriteTool executes arbitrary SQL provided by the caller using PDO::prepare + execute without semantic restrictions. This is consistent with the name “write tool”, but in an LLM/agent context it becomes a high-risk capability: prompt injection or indirect prompt manipulation can cause...
Neuron MySQLWriteTool allows arbitrary/destructive SQL when exposed to untrusted prompts (agent “footgun”)
Impact MySQLWriteTool executes arbitrary SQL provided by the caller using PDO::prepare + execute without semantic restrictions. This is consistent with the name “write tool”, but in an LLM/agent context it becomes a high-risk capability: prompt injection or indirect prompt manipulation can cause...
December 9, 2025—KB5071542 (OS Build 25398.2025)
None None...
Privacy Practices of Browser Agents
This paper presents a systematic evaluation of the privacy behaviors and attributes of eight recent, popular browser agents. Browser agents are software that automate Web browsing using large language models and ancillary tooling. However, the automated capabilities that make browser agents...
ThinkTrap: Denial-Of-Service Attacks against Black-Box LLM Services Via Infinite Thinking
Large Language Models LLMs have become foundational components in a wide range of applications, including natural language understanding and generation, embodied intelligence, and scientific discovery. As their computational requirements continue to grow, these models are increasingly deployed as...
nim-pentest-agent
NimPentestAgent Agent autonome de pentest intelligent pour CT...
Exploit for CVE-2025-55182
React 19 & Next.js Security Fix Prompts for AI Agents 🚨 CRI...
Whispering poetry at AI can make it break its own rules
Most of the big AI makers don't like people using their models for unsavory activity. Ask one of the mainstream AI models how to make a bomb or create nerve gas and you'll get the standard "I don't help people do harmful things" response. That has spawned a cat-and-mouse game of people who try to...
Malicious code in chat-prompt-logger (PyPI)
--- -= Per source details. Do not edit below this line.=- Source: kam193 f25a736985f5c0bb50156fdc7de61e976b16416f42c44a2682b5ce718401383b The package provides a logger of LLM prompts that at the same time looks for hidden instructions and executes them. --- Category: MALICIOUS - The campaign has...
MAL-2025-191699 Malicious code in chat-prompt-logger (PyPI)
--- -= Per source details. Do not edit below this line.=- Source: kam193 f25a736985f5c0bb50156fdc7de61e976b16416f42c44a2682b5ce718401383b The package provides a logger of LLM prompts that at the same time looks for hidden instructions and executes them. --- Category: MALICIOUS - The campaign has...
Prompt Injection Through Poetry
In a new paper, "Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models," researchers found that turning LLM prompts into poetry resulted in jailbreaking the models: Abstract : We present evidence that adversarial poetry functions as a universal single-turn...
Retrieval-Augmented Few-Shot Prompting Versus Fine-Tuning for Code Vulnerability Detection
Few-shot prompting has emerged as a practical alternative to fine-tuning for leveraging the capabilities of large language models LLMs in specialized tasks. However, its effectiveness depends heavily on the selection and quality of in-context examples, particularly in complex domains. In this wor...