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...

PromptPwnd Vulnerability Exposes AI driven build systems to Data Theft

Aikido Security exposes a new AI prompt injection flaw in GitHub/GitLab pipelines, letting attackers steal secrets. Major companies affected...

CVE-2025-66404

MCP Server Kubernetes is an MCP Server that can connect to a Kubernetes cluster and manage it. Prior to 2.9.8, there is a security issue exists in the execinpod tool of the mcp-server-kubernetes MCP Server. The tool accepts user-provided commands in both array and string formats. When a string...

DRUPAL-CONTRIB-2025-119

This modules provides the ability to chat with an AI Agent using a large-language model LLM provider for different purposes. The module doesn’t sufficiently filter LLM responses. This leads to a cross-site scripting XSS vulnerability where an attacker can use prompt injections on user-generated...

CVE-2025-66404: Improper Neutralization of Special Elements used in a Command

MCP Server Kubernetes is an MCP Server that can connect to a Kubernetes cluster and manage it. Prior to 2.9.8, there is a security issue exists in the execinpod tool of the mcp-server-kubernetes MCP Server. The tool accepts user-provided commands in both array and string formats. When a string...

AI (Artificial Intelligence) - Moderately critical - Cross-Site Scripting - SA-CONTRIB-2025-119

This modules provides the ability to chat with an AI Agent using a large-language model LLM provider for different purposes. The module doesn’t sufficiently filter LLM responses. This leads to a cross-site scripting XSS vulnerability where an attacker can use prompt injections on user-generated...

Malicious Package

Overview eslint-plugin-unicorn-ts-2 is a malicious package. This package uses typosquatting techniques, which are intended to trick users into downloading and installing the malicious package instead of the intended legitimate one. The malicious payload attempts to exfiltrate sensitive data from...

Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in Language Models

Whitepaper from researchers at MIT, Northeastern University, and Meta. For an LLM to correctly respond to an instruction it must understand both the semantics and the domain i.e., subject area of a given task-instruction pair. However, syntax can also convey implicit information Recent work shows...

A Wolf in Sheep's Clothing: Bypassing Commercial LLM Guardrails Via Harmless Prompt Weaving and Adaptive Tree Search

Large language models LLMs remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs. Existing approaches overwhelmingly operate within the prompt-optimization paradigm: whether through traditional algorithmic search or recent agent-based workflows, the...

openSUSE 16 Security Update : bash-git-prompt (openSUSE-SU-2025:20130-1)

The remote openSUSE 16 host has a package installed that is affected by a vulnerability as referenced in the openSUSE- SU-2025:20130-1 advisory. - CVE-2025-61659: Fixed an issue where predictable files in /tmp were used for a copy of the git index bsc1247489 Tenable has extracted the preceding...

COGNITION: From Evaluation to Defense against Multimodal LLM CAPTCHA Solvers

This paper studies how multimodal large language models MLLMs undermine the security guarantees of visual CAPTCHA. We identify the attack surface where an adversary can cheaply automate CAPTCHA solving using off-the-shelf models. We evaluate 7 leading commercial and open-source MLLMs across 18...

Securing Large Language Models (LLMs) from Prompt Injection Attacks

Large Language Models LLMs are increasingly being deployed in real-world applications, but their flexibility exposes them to prompt injection attacks. These attacks leverage the model's instruction-following ability to make it perform malicious tasks. Recent work has proposed JATMO, a task-specif...

Security update for bash-git-prompt (moderate)

openSUSE security update: security update for bash-git-prompt ------------------------------------------------------------- Announcement ID: openSUSE-SU-2025-20130-1 Rating: moderate References: bsc1247489 Cross-References: CVE-2025-61659 Affected Products: openSUSE Leap 16.0...

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...