CVE-2025-53097: Improper Neutralization of Special Elements in Output Used by a Downstream Component

Roo Code is an AI-powered autonomous coding agent. Prior to version 3.20.3, there was an issue where the Roo Code agent's searchfiles tool did not respect the setting to disable reads outside of the VS Code workspace. This means that an attacker who was able to inject a prompt into the agent coul...

CVE-2025-52573: Improper Neutralization of Special Elements used in an OS Command

iOS Simulator MCP Server ios-simulator-mcp is a Model Context Protocol MCP server for interacting with iOS simulators. Versions prior to 1.3.3 are written in a way that is vulnerable to command injection vulnerability attacks as part of some of its MCP Server tool definition and implementation. T...

CVE-2025-6431

When a link can be opened in an external application, Firefox for Android will, by default, prompt the user before doing so. An attacker could have bypassed this prompt, potentially exposing the user to security vulnerabilities or privacy leaks in external applications. This bug only affects...

CVE-2025-6431

When a link can be opened in an external application, Firefox for Android will, by default, prompt the user before doing so. An attacker could have bypassed this prompt, potentially exposing the user to security vulnerabilities or privacy leaks in external applications. This bug only affects...

UBUNTU-CVE-2025-6431

When a link can be opened in an external application, Firefox for Android will, by default, prompt the user before doing so. An attacker could have bypassed this prompt, potentially exposing the user to security vulnerabilities or privacy leaks in external applications. This bug only affects...

CVE-2025-6431

In Firefox for Android , a security bypass vulnerability exists in the Link Handler component where the prompt for opening links in external applications can be circumvented. This flaw could allow an attacker to bypass security restrictions, potentially leading to security vulnerabilities or priv...

CVE-2025-6431

When a link can be opened in an external application, Firefox for Android will, by default, prompt the user before doing so. An attacker could have bypassed this prompt, potentially exposing the user to security vulnerabilities or privacy leaks in external applications. This bug only affects...

CVE-2025-6431

When a link can be opened in an external application, Firefox for Android will, by default, prompt the user before doing so. An attacker could have bypassed this prompt, potentially exposing the user to security vulnerabilities or privacy leaks in external applications. This bug only affects...

Mozilla Firefox 安全漏洞

Mozilla Firefox is an open source web browser from the Mozilla Foundation in the United States. A security bypass vulnerability exists in Mozilla Firefox, which originates from External App Open Prompt for Android can be bypassed and can be exploited by attackers to bypass security restrictions...

CVE-2025-6431: Improper Authorization

When a link can be opened in an external application, Firefox for Android will, by default, prompt the user before doing so. An attacker could have bypassed this prompt, potentially exposing the user to security vulnerabilities or privacy leaks in external applications. This bug only affects...

Security Vulnerabilities fixed in Firefox 140 — Mozilla

A use-after-free in FontFaceSet resulted in a potentially exploitable crash. An attacker who enumerated resources from the WebCompat extension could have obtained a persistent UUID that identified the browser, and persisted between containers and normal/private browsing mode, but not profiles. Th...

Google Adds Multi-Layered Defenses to Secure GenAI from Prompt Injection Attacks

Google has revealed the various safety measures that are being incorporated into its generative artificial intelligence AI systems to mitigate emerging attack vectors like indirect prompt injections and improve the overall security posture for agentic AI systems. "Unlike direct prompt injections,...

Google Adds Multi-Layered Defenses to Secure GenAI from Prompt Injection Attacks

Google has revealed the various safety measures that are being incorporated into its generative artificial intelligence AI systems to mitigate emerging attack vectors like indirect prompt injections and improve the overall security posture for agentic AI systems. "Unlike direct prompt injections,...

Enhancing Security in LLM Applications: a Performance Evaluation of Early Detection Systems

Prompt injection threatens novel applications that emerge from adapting LLMs for various user tasks. The newly developed LLM-based software applications become more ubiquitous and diverse. However, the threat of prompt injection attacks undermines the security of these systems as the mitigation a...

Security Assessment of DeepSeek and GPT Series Models against Jailbreak Attacks

The widespread deployment of large language models LLMs has raised critical concerns over their vulnerability to jailbreak attacks, i.e., adversarial prompts that bypass alignment mechanisms and elicit harmful or policy-violating outputs. While proprietary models like GPT-4 have undergone extensi...

Scammers Use Inferno Drainer to Steal $43K from CoinMarketCap Users

Scammers used Inferno Drainer to steal $43,000 in crypto from 110 CoinMarketCap users through a fake wallet prompt embedded in the site’s front-end...

Alphabet Index Mapping: Jailbreaking LLMs through Semantic Dissimilarity

Large Language Models LLMs have demonstrated remarkable capabilities, yet their susceptibility to adversarial attacks, particularly jailbreaking, poses significant safety and ethical concerns. While numerous jailbreak methods exist, many suffer from computational expense, high token usage, or...

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks Via Security-Aware Prompt Compression

Large language models LLMs have achieved widespread adoption across numerous applications. However, many LLMs are vulnerable to malicious attacks even after safety alignment. These attacks typically bypass LLMs' safety guardrails by wrapping the original malicious instructions inside adversarial...

LLM-Based Dynamic Differential Testing for Database Connectors with Reinforcement Learning-Guided Prompt Selection

Database connectors are critical components enabling applications to interact with underlying database management systems DBMS, yet their security vulnerabilities often remain overlooked. Unlike traditional software defects, connector vulnerabilities exhibit subtle behavioral patterns and are...

VulStamp: Vulnerability Assessment Using Large Language Model

Although modern vulnerability detection tools enable developers to efficiently identify numerous security flaws, indiscriminate remediation efforts often lead to superfluous development expenses. This is particularly true given that a substantial portion of detected vulnerabilities either possess...