Malicious code in bigops-tcrm-auth (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 4f4cc9ef61d16a5c70a1adc9c2ab3acb9e51d650967f02621410285d99efd4a1 The package's main index.js requires./setup on load. setup.js selects a platform-specific payload path, downloads a native binary over HTTPS from...

Malicious code in beaver-ui-object-card (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 4a2a78be16248a4269fca22b39cf436f82f26818c797949af73eca331cc3a0f6 On require'beaver-ui-object-card', index.js loads ext.js which selects a platform-specific asset path and downloads an unsigned native binary from...

Malicious code in bnpl-blocks-atom-bnpl-feedback (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 058b0a78e0960f56198334ba1623fa948a0b198e4480910e73e44e48ad2704d0 On require'bnpl-blocks-atom-bnpl-feedback', index.js loads bridge.js which selects a platform-specific asset, downloads an unsigned binary via HTTPS...

Malicious code in node-cache-multithread (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 09be7b43b4fe5e0c786fb116e4a99518c46825e2b18b5e65eca88c51470b07a0 index.js, the package's declared main entry, is a 23KB obfuscator.io RC4/base64 string-array bundle whose top-level IIFE runs on require. It requires...

Malicious code in statist-browser-typed-client-sme.platform.mobile.voip.common.events (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector fb43194ddda04c3dffa5cb6bea02c8bc6edba8623acf172c5da744b2488e13b0 On require, compat.js selects a platform-specific payload path and downloads an opaque binary from one of four Cloudflare Workers hosts...

MAL-2026-12475 Malicious code in tcb-web-copy-to-clipboard (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector e17b4feb97874ea6bf112238baf911ef3ebb815f12034b726c8b1a5d1705adbb The package advertises itself as a clipboard SDK, but index.js requires./setup at load, which selects a platform-specific payload path, fetches bytes...

MAL-2026-12077 Malicious code in tinkoff-statist-browser-typed-client-sme.compliance.web.events (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 65171e84f70bed8b30e494c9ab147abc3c26207ba7b3fb9ccf348cf8746867e4 The package's declared main entry index.js unconditionally requires./init on load. init.js assembles hardcoded remote hosts from split string fragmen...

Stateful Cooperative Agents Safeguarding LLMs against Evolving Multi-Turn Attacks

As LLMs become increasingly integrated into complex applications, their vulnerability to adversarial attacks has raised significant concerns. However, existing defenses remain reactive in nature. This limitation makes it difficult for them to counter sophisticated threats, as adversaries...

DEBIAN-CVE-2026-17976

Insufficient policy enforcement in Extensions in Google Chrome prior to 151.0.7922.72 allowed an attacker who convinced a user to install a malicious extension to bypass discretionary access control via a crafted domain name. Chromium security severity: Low...

CVE-2026-17755

Incorrect security UI in Extensions in Google Chrome prior to 151.0.7922.72 allowed an attacker who convinced a user to install a malicious extension to perform UI spoofing via a crafted Chrome Extension. Chromium security severity: Medium...

CVE-2026-17755

Incorrect security UI in Extensions in Google Chrome prior to 151.0.7922.72 allowed an attacker who convinced a user to install a malicious extension to perform UI spoofing via a crafted Chrome Extension. Chromium security severity: Medium...

PT-2026-66140

Name of the Vulnerable Software and Affected Versions Google Chrome versions prior to 151.0.7922.72 Description Insufficient policy enforcement in Extensions allows an attacker to bypass navigation restrictions. This occurs when a user is convinced to install a crafted malicious extension...

Agent Harness Distillation: Inference-Time Harness Extraction and Exploitation in Autonomous Multi-Agent Systems

Autonomous multi-agent systems AMAS built on large language models LLMs, such as Hermes, increasingly rely on inference-time harnesses to coordinate reasoning and action. Constructing these harnesses requires substantial engineering effort and computational resources, as they are iteratively...

AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Penetration Agents

Large language model LLM agents automate penetration testing through an observation-action loop, selecting actions based on observations returned by tools. This dependence allows defenders to inject deceptive observations that can mislead the agent's decision-making process. However, existing...

Agentic Cloud Decoys: A Deception-Driven Framework for Autonomous Intrusion Investigation

Cloud telemetry arrives at a scale that, paradoxically, makes intrusion understanding harder rather than easier. Attackers operate through legitimate identity, federated session tokens, and cloud native APIs indistinguishable from routine administration, and analysts spend an incident...

Astra Linux – Vulnerability in Chromium

Insufficient policy enforcement in extensions in Google Chrome on Linux prior to 150.0.7871.47 allowed an attacker who convinced a user to install a malicious extension to perform UI spoofing via a crafted Chrome extension. Chromium security severity: Medium...

honeyprompt v0.1.8

honeyprompt Introducing honeyprompt, an LLM-first deception framework made by/for web developers. The personal passion project of @alectrocute. Supports all major cloud and local LLM providers. SSH, HTTP, TLS, TCP, telnet and more. It ships as a small container and a single static binary and keep...

MAL-2026-10933 Malicious code in twilio-deploy (npm)

The twilio-deploy package is one of four byte-identical dependency-confusion squats of Twilio's npm namespace published by user 'yuva2210' maintainer email [email protected], all at the sentinel version 99.99.99 chosen to outrank any internal/private version and win resolution against a...

terminal-poc-corpus

terminal-poc-corpus A defensive, machine-readable corpus...

DICOMHawk: A Cyber Deception Framework for Medical Imaging Infrastructure

Cyber-attacks against exposed healthcare infrastructure threaten sensitive patient data and clinical operations, yet existing defensive tools for DICOM-based medical imaging systems provide limited interaction and are easily fingerprinted. We introduce DICOMHawk, a cyber-deception framework that...