Critical LangChain Core Vulnerability Exposes Secrets via Serialization Injection

A critical security flaw has been disclosed in LangChain Core that could be exploited by an attacker to steal sensitive secrets and even influence large language model LLM responses through prompt injection. LangChain Core i.e., langchain-core is a core Python package that's part of the LangChain...

Eurostar Accused Researchers of Blackmail for Reporting AI Chatbot Flaws

Researchers discovered critical flaws in Eurostar’s AI chatbot including prompt injection, HTML injection, guardrail bypass, and unverified chat IDs - Eurostar later accused them of blackmail...

From Agent2Agent Prompt Injection to Runtime Self-Defense: How Wallarm Redefines Agentic AI Security

Is an AI-to-AI attack scenario a science fiction possibility only for blockbusters like the Terminator series of movies? Well, maybe not! Researchers recently discovered that one AI agent can “inject malicious instructions into a conversation, hiding them among otherwise benign client requests an...

Moodle Prompt Injection Vulnerability (MSA-25-0053)

Moodle is prone to a prompt injection vulnerability. SPDX-FileCopyrightText: 2025 Greenbone AG Some text descriptions might be excerpted from a referenced sources, and are Copyright C by the respective right holders. SPDX-License-Identifier: GPL-2.0-only CPE = "cpe:/a:moodle:moodle"; ifdescriptio...

CVE-2025-63665

An issue in GT Edge AI Community Edition Versions before v2.0.12 allows attackers to execute arbitrary code via injecting a crafted JSON payload into the Prompt window...

Docker Fixes ‘Ask Gordon’ AI Flaw That Enabled Metadata-Based Attacks

Pillar Security has identified a critical indirect prompt injection vulnerability in Docker’s ‘Ask Gordon’ assistant. By poisoning metadata on Docker Hub, attackers could bypass security to exfiltrate private build logs and chat history. Discover how the "lethal trifecta" enabled this attack and...

Penetration Testing of Agentic AI: A Comparative Security Analysis across Models and Frameworks

Agentic AI introduces security vulnerabilities that traditional LLM safeguards fail to address. Although recent work by Unit 42 at Palo Alto Networks demonstrated that ChatGPT-4o successfully executes attacks as an agent that it refuses in chat mode, there is no comparative analysis in multiple...

Arbitrary Command Injection

mcp-server-kubernetes is vulnerable to Arbitrary Command Injection. The vulnerability is due to passing user-supplied command strings directly to shell execution sh -c without input validation, which allows an attacker to inject and execute arbitrary commands through crafted inputs or indirect...

Detecting Prompt Injection Attacks against Application Using Classifiers

Prompt injection attacks can compromise the security and stability of critical systems, from infrastructure to large web applications. This work curates and augments a prompt injection dataset based on the HackAPrompt Playground Submissions corpus and trains several classifiers, including LSTM,...

CeLLMate: Sandboxing Browser AI Agents

Browser-using agents BUAs are an emerging class of autonomous agents that interact with web browsers in human-like ways, including clicking, scrolling, filling forms, and navigating across pages. While these agents help automate repetitive online tasks, they are vulnerable to prompt injection...

CVE-2025-67510

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...

Scale AI Securely with Qualys TotalAI’s Streamlined Onboarding, Deeper Risk Detection, and Compliance-Ready Reporting

Executive Summary Enterprises are entering a phase where AI systems function as decision engines that shape customer interactions, operational workflows, and business outcomes. This creates a new class of risk that is behavioral, contextual, and dynamic, driven by how models interpret instruction...

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...

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...

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...

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...

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...