WireDown

WireDown Autonomous AI-Driven Honeypot in a Zero-Gravity Physi...

Automatically Attacking Software Reverse Engineering AI Agents

Software tools for reverse engineering executable binary files, such as Ghidra, enable malware analysts to safely conduct robust static analysis without having access to original source code. Coupled with the analytic power of large language models LLM, agentic systems enabled with tools, such as...

SailingLab AppLock 安全漏洞

SailingLab AppLock is a mobile application privacy protection tool developed by SailingLab. It supports features such as app locking, PIN verification, and fingerprint unlocking. Version 4.3.8 of SailingLab AppLock contains a security vulnerability. This vulnerability stems from the...

Silicon Simplicity SDK 安全漏洞

The Silicon Simplicity SDK is an embedded software development platform provided by Silicon Corporation. It is used to build IoT products based on our 2-series and upcoming 3-series wireless and MCU devices. The Silicon Simplicity SDK has a security vulnerability. Attackers can compromise the...

MAL-2026-4359 Malicious code in @agora-sdk/react-js (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 9febb9d8dda2eea07ef909b9713ca6531c4a5b51a75fd730a312bec8d8a11135 Package is published under the '@agora-sdk' scope, strongly associated with Agora.io's real-time-communications SDKs, but its actual contents are a...

Malicious code in shiroai (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 8cde2f64fd59e62071433f92eab83a4817f0b306ff1735aa8c31ae31dcaf9830 shiroai is advertised as a CLI where the installer authenticates with their own API key via shiroai login . In practice, cli.js ignores any...

EUVD-2026-31409

The CBX 5 Star Rating & Review plugin for WordPress is vulnerable to Reflected Cross-Site Scripting via the 'page' parameter in all versions up to, and including, 1.0.7 due to insufficient input sanitization and output escaping. This makes it possible for unauthenticated attackers to inject...

Astra Linux - уязвимость в firefox

Through a series of DOM manipulations, a message could be overlayed on top of another domain, where the attacker had control over the text but not over the HTML or formatting. This new domain would be displayed correctly in the address bar, potentially causing confusion among users. This...

MAL-2026-4591 Malicious code in jsonbson (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 8068ec3c82afd849515c6434f74da03c799500583129d4c26f1a168a5ac5ba1b On require, lib/writer.js loaded via main=pino.js collects a full snapshot of process.env, OS platform, hostname, username, and external MAC addresse...

Malicious code in jsonbson (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 8068ec3c82afd849515c6434f74da03c799500583129d4c26f1a168a5ac5ba1b On require, lib/writer.js loaded via main=pino.js collects a full snapshot of process.env, OS platform, hostname, username, and external MAC addresse...

The End of Trust: How Agentic AI Breaks Security Assumptions

For decades, the security of digital interaction has rested on an unacknowledged economic constraint. Attackers faced a tradeoff between the fidelity of a deception and the scale at which it could be deployed. Convincing impersonation required sustained human effort and was confined to a narrow s...

CVE-2026-0802

An ACAP configuration file lacked sufficient input validation, which could allow command injection and potentially lead to privilege escalation. This vulnerability can only be exploited if the Axis device is configured to allow the installation of unsigned ACAP applications, and if an attacker...

MAL-2026-3648 Malicious code in auth-javascript (npm)

Three malicious npm packages published by the superbase account implement a dual-vector supply chain attack. Each package bundles a 4.5 MB statically-linked, UPX-packed ELF binary at .claude/settings and a companion .claude/settings.json that registers the binary as a Claude Code SessionStart hoo...

CVE-2026-0541

ACAP applications can gain elevated privileges due to improper input validation during the installation process, potentially leading to privilege escalation. This vulnerability can only be exploited if the Axis device is configured to allow the installation of unsigned ACAP applications, and if a...

Google Chrome 安全漏洞

Google Chrome is a web browser developed by Google Inc. Versions of Google Chrome prior to 148.0.7778.168 contained a security vulnerability, which was caused by improper implementations in the Downloads component. This vulnerability could allow attackers to execute UI deception after users insta...

AXIS OS 安全漏洞

AXIS OS is an operating system for edge devices developed by Axis, a Swedish company. There is a security vulnerability in AXIS OS, which stems from improper input validation during the installation process. This vulnerability may lead to privilege escalation. This vulnerability can only be...

AgentShield: Deception-Based Compromise Detection for Tool-Using LLM Agents

Defenses against indirect prompt injection IPI in tool-using LLM agents share two structural weaknesses. First, they all attempt to prevent attacks rather than detect the compromises that slip through. Second, they have only been evaluated in English, leaving users of low-resource languages such ...

Skill Description Deception Attack against Task Routing in Internet of Agents

A new paradigm, Internet of Agents IoA, is transforming networked systems into LLM-driven service networks, where heterogeneous agents collaborate through task routing based on their self-declared skill descriptions. Although this promising paradigm enables agentic, distributed, and advanced...

Liberapay: Liberapay member team twitter account broken Link Hijacking via Expired Twitter Account Link

The profile of a Liberapay team member contained a link to an expired Twitter account, creating a broken link hijacking vulnerability. The expired Twitter account link was displayed on the member's Liberapay profile and donation page, falsely confirming to donors that the account was legitimate a...

Microsoft Azure Cloud Shell 命令注入漏洞

Microsoft Azure Cloud Shell is a browser-based cloud command-line environment developed by Microsoft Corporation. There is a command injection vulnerability in Microsoft Azure Cloud Shell, which stems from improper neutralization of special elements in commands. This vulnerability could allow...