Manipulating-Web-Agents

Manipulación de agentes web autónomos basados en LLM mediante ataques de inyección indirecta de prompts Con la ubicuidad de las aplicaciones integradas con LLM, investigar los posibles riesgos de seguridad es crucial. Una de las vulnerabilidades más significativas de estos sistemas es su...

IPI-exposure-signal

IPI Exposure Signal Este es el repositorio de código de nuestro artículo: Your Agentic LLMs Secretly Encode Latent Signals of Indirect Prompt-Injection Exposure. Versión en arXiv y enlace al artículo: https://arxiv.org/abs/2608.02657 Este repositorio implementa el pipeline de sondeo para señales...

llm-security

Nuevo: Demostración de ataques de inyección indirecta en Bing Chat Comprometer LLMs mediante inyección indirecta de prompts "... un modelo de lenguaje es una máquina extraña Turing-completa que ejecuta programas escritos en lenguaje natural; cuando haces recuperación, no estás 'conectando hechos...

ROPE

ROPE: Aplicación de Política de Origen Enrutado Código fuente de nuestro artículo: ROPE: Aplicación de Política de Origen Enrutado contra la Inyección Indirecta de Prompts por Xinhang Ma, Chaowei Xiao, William Yeoh, Ning Zhang, Yevgeniy Vorobeychik Resumen La inyección indirecta de prompts IPI...

prompt-injection-email-samples

Muestras de correo con inyección de prompt Un conjunto de pruebas abierto y reducido de correos electrónicos para comprobar si tus controles de seguridad de correo electrónico y asistentes de buzón con IA manejan la inyección indirecta de prompt : instrucciones ocultas en un correo electrónico qu...

Can CaMeLs Talk? Securing Multi-Agent Systems against Indirect Prompt Injection Attacks

Indirect prompt injection attacks - malicious instructions embedded in content processed by large language models - remain a major obstacle to safely deploying tool-using agents. CaMeL Debenedetti et al., 2025 mitigates this threat for an individual agent by separating trusted control flow from...

Who Is Your Agent Serving? Provider-Side Indirect Prompt Injection in Proactive Agents

Proactive personal agents increasingly decide what to recommend, how to personalize advice, and what follow-up assistance to offer, creating a new user-decision attack surface for provider-side indirect prompt injection. We show that an external provider need not access private user context,...

CVE-2026-96561

The AI Engine – The Chatbot, AI Framework & MCP for WordPress plugin for WordPress is vulnerable to Stored Cross-Site Scripting in versions up to, and including, 3.8.0 This is due to a chain of missing input neutralization and output escaping across the /mwai-ui/v1/chats/submit REST endpoint, the...

CVE-2026-96561

The AI Engine – The Chatbot, AI Framework & MCP for WordPress plugin is vulnerable to Stored Cross-Site Scripting (XSS) in versions up to and including 3.8.0 . The vulnerability stems from a chain of missing input neutralization and output escaping starting at the /mwai-ui/v1/chats/submit REST en...

EUVD-2026-90465

The AI Engine – The Chatbot, AI Framework & MCP for WordPress plugin for WordPress is vulnerable to Stored Cross-Site Scripting in versions up to, and including, 3.8.0 This is due to a chain of missing input neutralization and output escaping across the /mwai-ui/v1/chats/submit REST endpoint, the...

CVE-2026-96561 AI Engine <= 3.8.0 - Unauthenticated Stored Cross-Site Scripting via 'model_' Parameter → PHP Error-Log Injection → Advisor Indirect Prompt Injection

The AI Engine – The Chatbot, AI Framework & MCP for WordPress plugin for WordPress is vulnerable to Stored Cross-Site Scripting in versions up to, and including, 3.8.0 This is due to a chain of missing input neutralization and output escaping across the /mwai-ui/v1/chats/submit REST endpoint, the...

CVE-2026-96561 AI Engine <= 3.8.0 - Unauthenticated Stored Cross-Site Scripting via 'model_' Parameter → PHP Error-Log Injection → Advisor Indirect Prompt Injection

The AI Engine – The Chatbot, AI Framework & MCP for WordPress plugin for WordPress is vulnerable to Stored Cross-Site Scripting in versions up to, and including, 3.8.0 This is due to a chain of missing input neutralization and output escaping across the /mwai-ui/v1/chats/submit REST endpoint, the...

ActGuard

ActGuard ActGuard es una defensa de auditoría de acciones previa a la ejecución contra la inyección indirecta de prompts en agentes LLM que utilizan herramientas. Este repositorio contiene la implementación final de ActGuard y el entorno de ejecución basado en AgentDojo necesario para evaluarla. ...

From A2A Attacks to Envelope-Layer Defense: Red-Teaming Evaluation of LLM Agents and a Three-Layer Isomorphic Attack-Defense Model

Agent interaction protocols such as ACP and A2A have moved LLM-based agents toward multi-agent collaboration, introducing new security threats. A task sent by a remote peer over A2A is treated as a legitimate request, providing a natural channel for indirect prompt injection. Existing agent...

MetaPermit: Scalable and Auditable Access Control for AI Agents Via LLM-Inferred Meta-Attributes

The rise of autonomous AI agents equipped with tools has introduced significant security risks, ranging from unintended tool misuse to adversarial manipulation through Indirect Prompt Injection IPI attacks. In practice, deployed agent systems such as OpenAI Codex and Claude Code protect tool...

PT-2026-85580

LaVague 0.2.35 contains a remote code execution vulnerability in PythonFromMarkdownExtractor.extract as object that evaluates untrusted language model output derived from web page content. Attackers can inject malicious Python code through web pages using indirect prompt injection to execute...

CVE-2026-85694: Improper Control of Generation of Code

LaVague 0.2.35 contains a remote code execution vulnerability in PythonFromMarkdownExtractor.extractasobject that evaluates untrusted language model output derived from web page content. Attackers can inject malicious Python code through web pages using indirect prompt injection to execute...

CVE-2026-82217: Improper Limitation of a Pathname to a Restricted Directory

In Eclipse Theia versions 1.73.0 up to but not including 1.75.0, the AI "Agent Mode" file-change tools writeFileContent, suggestFileContent, and the replacement and state helpers resolved a model-supplied file path without a workspace-containment check. A crafted relative path such as ../.bashrc,...

leash-poc

leash-poc: MCP tool-poisoning, contained by an independent pol...

When Agents Go Rogue: The OpenClaw Supply Chain Crisis

When Agents Go Rogue: The OpenClaw Supply Chain Crisis By Aniket Choukde, Vikas Mishra and Yadunadh · August 19, 2026 This blog was also written by Akhil Reddy and Pavan Kumar Podila Executive Summary The cybersecurity landscape is currently undergoing a seismic shift driven by the adoption of...