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...

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...

CVE-2025-63665

GT Edge AI Community Edition (versions before v2.0.12 ) and GT Edge AI Platform (versions prior to v2.0.10-dev ) are vulnerable to arbitrary code execution . The root cause is the improper control of generation of code (CWE-94), where an attacker can inject a crafted JSON payload into the Prompt ...

PT-2025-52498

Name of the Vulnerable Software and Affected Versions GT Edge AI Platform versions prior to 2.0.10-dev Description An issue in GT Edge AI Platform allows attackers to execute arbitrary code by injecting a crafted JSON payload into the Prompt window. The vulnerability involves the potential for co...

CVE-2025-63665: Improper Control of Generation of Code

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...

Jailbreak-Zero: A Path to Pareto Optimal Red Teaming for Large Language Models

This paper introduces Jailbreak-Zero, a novel red teaming methodology that shifts the paradigm of Large Language Model LLM safety evaluation from a constrained example-based approach to a more expansive and effective policy-based framework. By leveraging an attack LLM to generate a high volume of...

Trust in LLM-Controlled Robotics: A Survey of Security Threats, Defenses and Challenges

The integration of Large Language Models LLMs into robotics has revolutionized their ability to interpret complex human commands and execute sophisticated tasks. However, such paradigm shift introduces critical security vulnerabilities stemming from the ''embodiment gap'', a discord between the...

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...

CVE-2025-14019

LINE client for Android versions from 13.8 to 15.5 is vulnerable to UI spoofing in the in-app browser where a specific layout could obscure the full-screen warning prompt, potentially allowing attackers to conduct phishing attacks...

EUVD-2025-203349

LINE client for Android versions from 13.8 to 15.5 is vulnerable to UI spoofing in the in-app browser where a specific layout could obscure the full-screen warning prompt, potentially allowing attackers to conduct phishing attacks...

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...

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...

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,...

Securing GenAI in the Browser: Policy, Isolation, and Data Controls That Actually Work

The browser has become the main interface to GenAI for most enterprises: from web-based LLMs and copilots, to GenAI‑powered extensions and agentic browsers like ChatGPT Atlas. Employees are leveraging the power of GenAI to draft emails, summarize documents, work on code, and analyze data, often b...

PT-2025-51038

Name of the Vulnerable Software and Affected Versions Apple products affected versions not specified Description A permissions issue was identified and addressed through the implementation of additional restrictions. Recommendations At the moment, there is no information about a newer version tha...

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...

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...

CVE-2025-66451 LibreChat's Improper Input Validation in Prompt Creation API Enables Unauthorized Permission Changes

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-2025-66451 LibreChat's Improper Input Validation in Prompt Creation API Enables Unauthorized Permission Changes

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...