CVE-2026-33324

SQLBot is an intelligent Text-to-SQL system based on large language models and RAG. In versions 1.7.0 and earlier, the Text2SQL chat interface is vulnerable to prompt injection. The user-provided question parameter is directly concatenated into the LLM prompt without filtering or escaping, and th...

EUVD-2026-27446

SQLBot is an intelligent Text-to-SQL system based on large language models and RAG. In versions 1.7.0 and earlier, the Text2SQL chat interface is vulnerable to prompt injection. The user-provided question parameter is directly concatenated into the LLM prompt without filtering or escaping, and th...

CVE-2026-33324

SQLBot’s Text-to-SQL prompt injection vulnerability affects versions 1.7.0 and earlier, where the user’s question is concatenated into the LLM prompt and the resulting SQL is executed without validation. An authenticated attacker can craft a malicious query to coerce the LLM into generating and r...

PT-2026-37219

Name of the Vulnerable Software and Affected Versions SQLBot versions prior to 1.7.1 Description The Text2SQL chat interface is susceptible to prompt injection. The question parameter is concatenated into the Large Language Model LLM prompt without filtering or escaping, and the resulting SQL is...

ARGUS: Defending LLM Agents against Context-Aware Prompt Injection

The rise of Large Language Model LLM agents, augmented with tool use, skills, and external knowledge, has introduced new security risks. Among them, prompt injection attacks, where adversaries embed malicious instructions into the agent workflow, have emerged as the primary threat. However,...

PIIGuard: Mitigating PII Harvesting under Adversarial Sanitization

Browsing-enabled LLM assistants can fetch webpages and answer contact-seeking queries, creating a practical channel for scraping contact-style personally identifiable information PII from public pages. Many prior defenses are deployed at the model, service, or agent layer rather than at the webpa...

The (In)security Landscape of AI-Powered GitHub Actions (Part 2/2)

When AI meets CI/CD: permission bypasses, prompt injection, and what to do about it...

OpenClaw: Webchat audio embedding could read local files without local-root containment

Impact OpenClaw deployments before 2026.4.15 could embed host-local audio files into webchat responses without applying the local media root containment check used by other media-serving paths. If an attacker could influence an agent or tool-produced ReplyPayload.mediaUrl, the webchat audio...

CVE-2026-24222

NVIDIA NeMoClaw contains a vulnerability in the sandbox environment initialization component, where a remote attacker could cause improper access control by sending prompt-injected content that causes the agent to read and exfiltrate host environment variables not properly restricted during sandb...

Indirect Prompt Injection in the Wild: An Empirical Study of Prevalence, Techniques, and Objectives

As LLMs are increasingly integrated into systems that browse, retrieve, summarize, and act on web content, webpages have become an untrusted input vector for downstream model behavior. This enables site owners, contributors, and adversaries to embed instructions directly in web resources, i.e.,...

CVE-2026-24222

NVIDIA NeMoClaw contains a vulnerability in the sandbox environment initialization component, where a remote attacker could cause improper access control by sending prompt-injected content that causes the agent to read and exfiltrate host environment variables not properly restricted during sandb...

CVE-2026-24222

NVIDIA NeMoClaw contains a vulnerability in the sandbox environment initialization component, where a remote attacker could cause improper access control by sending prompt-injected content that causes the agent to read and exfiltrate host environment variables not properly restricted during sandb...

CVE-2026-24222

NVIDIA NeMoClaw contains a vulnerability in the sandbox environment initialization component, where a remote attacker could cause improper access control by sending prompt-injected content that causes the agent to read and exfiltrate host environment variables not properly restricted during sandb...

CVE-2026-24222

NVIDIA NemoClaw vulnerability CVE-2026-24222 affects the sandbox environment initialization component. A remote attacker can cause improper access control by sending prompt-injected content, leading to reading/exfiltrating host environment variables not properly restricted during sandbox creation...

EUVD-2026-26079

NVIDIA NeMoClaw contains a vulnerability in the sandbox environment initialization component, where a remote attacker could cause improper access control by sending prompt-injected content that causes the agent to read and exfiltrate host environment variables not properly restricted during sandb...

CVE-2026-24222

NVIDIA NeMoClaw contains a vulnerability in the sandbox environment initialization component, where a remote attacker could cause improper access control by sending prompt-injected content that causes the agent to read and exfiltrate host environment variables not properly restricted during sandb...

PT-2026-35756

NVIDIA NeMoClaw contains a vulnerability in the sandbox environment initialization component, where a remote attacker could cause improper access control by sending prompt-injected content that causes the agent to read and exfiltrate host environment variables not properly restricted during sandb...

Logic-to-Code Execution via Indirect Prompt Injection

This document explores a critical architectural vulnerability in Large Language Model LLM implementations, specifically within Command Line Interface CLI tools and automated agentic workflows. The research demonstrates how the absence of separation between the control plane instructions and the...

AgentVisor: Defending LLM Agents against Prompt Injection Via Semantic Virtualization

Large Language Model LLM agents are increasingly used to automate complex workflows, but integrating untrusted external data with privileged execution exposes them to severe security risks, particularly direct and indirect prompt injection. Existing defenses face significant challenges in balanci...

Evaluation of Prompt Injection Defenses in Large Language Models

LLM-powered applications routinely embed secrets in system prompts, yet models can be tricked into revealing them. We built an adaptive attacker that evolves its strategies over hundreds of rounds and tested it against nine defense configurations across more than 20,000 attacks. Every defense tha...