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...

CVE-2025-66451: Improper Input Validation

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...

CVE-2025-67509

Neuron is a PHP framework for creating and orchestrating AI Agents. Versions 2.8.11 and below use MySQLSelectTool, which is vulnerable to Read-Only Bypass. MySQLSelectTool is intended to be a read-only SQL tool e.g., for LLM agent querying, however, validation based on the first keyword e.g.,...

CVE-2025-67509 MySQLSelectTool Read-Only Bypass via SELECT INTO OUTFILE Allows Arbitrary File Write

Neuron is a PHP framework for creating and orchestrating AI Agents. Versions 2.8.11 and below use MySQLSelectTool, which is vulnerable to Read-Only Bypass. MySQLSelectTool is intended to be a read-only SQL tool e.g., for LLM agent querying, however, validation based on the first keyword e.g.,...

CVE-2025-67509 MySQLSelectTool Read-Only Bypass via SELECT INTO OUTFILE Allows Arbitrary File Write

Neuron is a PHP framework for creating and orchestrating AI Agents. Versions 2.8.11 and below use MySQLSelectTool, which is vulnerable to Read-Only Bypass. MySQLSelectTool is intended to be a read-only SQL tool e.g., for LLM agent querying, however, validation based on the first keyword e.g.,...

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...

PT-2025-50555

Name of the Vulnerable Software and Affected Versions Neuron versions 2.8.11 and below Description Neuron is a PHP framework used for creating and orchestrating AI Agents. The framework utilizes MySQLSelectTool, which has a Read-Only Bypass issue. The tool’s validation, based on the first keyword...

PT-2025-50556

Name of the Vulnerable Software and Affected Versions Neuron versions prior to 2.8.12 Description The PHP framework Neuron has an issue where the MySQLWriteTool can execute arbitrary SQL queries provided by a caller, utilizing PDO::prepare and execute without restrictions. This occurs because the...

LLM-PEA: Leveraging Large Language Models against Phishing Email Attacks

Email phishing is one of the most prevalent and globally consequential vectors of cyber intrusion. As systems increasingly deploy Large Language Models LLMs applications, these systems face evolving phishing email threats that exploit their fundamental architectures. Current LLMs require...

CVE-2025-67510: Execution with Unnecessary Privileges

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...

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...

Open Redirect

Overview taguette is a Free and open source qualitative research tool Affected versions of this package are vulnerable to Open Redirect via the next parameter in the login and cookies prompt processes. An attacker can redirect users to arbitrary external websites by crafting malicious URLs...

GHSA-5923-R76V-MPRM Open Redirect Vulnerability in Taguette

Summary An Open Redirect vulnerability exists in Taguette that allows attackers to craft malicious URLs that redirect users to arbitrary external websites after authentication. This can be exploited for phishing attacks where victims believe they are interacting with a trusted Taguette instance b...

Prompt injection is a problem that may never be fixed, warns NCSC

Prompt injection is shaping up to be one of the most stubborn problems in AI security, and the UK’s National Cyber Security Centre NCSC has warned that it may never be “fixed” in the way SQL injection was. Two years ago, the NCSC said prompt injection might turn out to be the “SQL injection of th...

Google Adds Layered Defenses to Chrome to Block Indirect Prompt Injection Threats

Google on Monday announced a set of new security features in Chrome, following the company's addition of agentic artificial intelligence AI capabilities to the web browser. To that end, the tech giant said it has implemented layered defenses to make it harder for bad actors to exploit indirect...

December 9, 2025—KB5071507 (Security-only update)

None None...

KB5074204: Security Update for Windows PowerShell (OS Builds 26100.7392 and 26200.7392)

None None...

CVE-2025-48597

In multiple locations, there is a possible way to trick a user into accepting a permission due to a tapjacking/overlay attack. This could lead to local escalation of privilege with no additional execution privileges needed. User interaction is not needed for exploitation...

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...

Researcher Uncovers 30+ Flaws in AI Coding Tools Enabling Data Theft and RCE Attacks

Over 30 security vulnerabilities have been disclosed in various artificial intelligence AI-powered Integrated Development Environments IDEs that combine prompt injection primitives with legitimate features to achieve data exfiltration and remote code execution. The security shortcomings have been...