PINA: Prompt Injection Attack against Navigation Agents

Navigation agents powered by large language models LLMs convert natural language instructions into executable plans and actions. Compared to text-based applications, their security is far more critical: a successful prompt injection attack does not just alter outputs but can directly misguide...

A Prompt-Based Framework for Loop Vulnerability Detection Using Local LLMs

Loop vulnerabilities are one major risky construct in software development. They can easily lead to infinite loops or executions, exhaust resources, or introduce logical errors that degrade performance and compromise security. The problem are often undetected by traditional static analyzers becau...

Ubuntu: Security Advisory (USN-7964-1)

The remote host is missing an update for the SPDX-FileCopyrightText: 2026 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 ifdescription...

MiracleLinux 8 : firefox-91.9.0-1.el8.ML.1 (AXSA:2022-3174:10)

The remote MiracleLinux 8 host has a package installed that is affected by multiple vulnerabilities as referenced in the AXSA:2022-3174:10 advisory. Mozilla: Bypassing permission prompt in nested browsing contexts CVE-2022-29909 Mozilla: iframe Sandbox bypass CVE-2022-29911 Mozilla: Fullscreen...

MiracleLinux 8 : zsh-5.5.1-9.el8 (AXSA:2022-3376:01)

The remote MiracleLinux 8 host has packages installed that are affected by a vulnerability as referenced in the AXSA:2022-3376:01 advisory. zsh: Prompt expansion vulnerability CVE-2021-45444 Tenable has extracted the preceding description block directly from the MiracleLinux security advisory. No...

Google Gemini Prompt Injection Flaw Exposed Private Calendar Data via Malicious Invites

Cybersecurity researchers have disclosed details of a security flaw that leverages indirect prompt injection targeting Google Gemini as a way to bypass authorization guardrails and use Google Calendar as a data extraction mechanism. The vulnerability, Miggo Security's Head of Research, Liad...

SUSE CVE-2026-22687

WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.2.5, after WeKnora enables the Agent service, it allows users to call the database query tool. Due to insufficient backend validation, an attacker can use prompt-based bypass...

MiracleLinux 7 : gvfs-1.36.2-3.el7 (AXSA:2019-4036:01)

The remote MiracleLinux 7 host has packages installed that are affected by a vulnerability as referenced in the AXSA:2019-4036:01 advisory. gvfs: Incorrect authorization in admin backend allows privileged users to read and modify arbitrary files without prompting for password CVE-2019-3827 Tenabl...

MiracleLinux 7 : nautilus-3.22.3-4.el7 (AXSA:2018-2543:01)

The remote MiracleLinux 7 host has packages installed that are affected by a vulnerability as referenced in the AXSA:2018-2543:01 advisory. An untrusted .desktop file with executable permission set could choose its displayed name and icon, and execute commands without warning when opened by the...

The Librarian does not secure its interface, allowing for access to internal system data

Overview Multiple vulnerabilities were discovered in The Librarian, an AI-powered personal assistant tool provided by the company TheLibrarian.io. The Librarian can be used to manage personal email, calendar, documents, and other information through external services, such as Gmail and Google...

CVE-2026-22708

Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via...

USN-7964-1 git vulnerabilities

It was discovered that Git did not properly sanitize URLs when asking for credentials via a terminal prompt. An attacker could possibly use this issue to trick a user into disclosing their password. CVE-2024-50349 It was discovered that Git did not properly handle carriage return characters in it...

“Reprompt” attack lets attackers steal data from Microsoft Copilot

Researchers found a method to steal data which bypasses Microsoft Copilot's built-in safety mechanisms. The attack flow, called Reprompt , abuses how Microsoft Copilot handled URL parameters in order to hijack a user’s existing Copilot Personal session. Copilot is an AI assistant which connects t...

Model Security Is the Wrong Frame – The Real Risk Is Workflow Security

As AI copilots and assistants become embedded in daily work, security teams are still focused on protecting the models themselves. But recent incidents suggest the bigger risk lies elsewhere: in the workflows that surround those models. Two Chrome extensions posing as AI helpers were recently...

Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale

The rise of AI agent frameworks has introduced agent skills, modular packages containing instructions and executable code that dynamically extend agent capabilities. While this architecture enables powerful customization, skills execute with implicit trust and minimal vetting, creating a...

CVE-2026-22708

Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via...

CVE-2026-22708 Cursor has a Terminal Tool Allowlist Bypass via Environment Variables

Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via...

EUVD-2026-2678

Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via...

CVE-2026-22708

Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via...

CVE-2026-22708 Cursor has a Terminal Tool Allowlist Bypass via Environment Variables

Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via...