Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM Security

Large Language Models LLMs are increasingly vulnerable to adversarial prompts that exploit semantic ambiguities to bypass safety mechanisms, resulting in harmful or inappropriate outputs. Such attacks, including jailbreaking and prompt injection, pose significant risks to the integrity and...

Toxic_Flow_Analysis_Framework_For_Agentic_AI

Toxic Flow Analysis TFA Framework A Secure-by-Design framew...

What Is Exposure Management? A Proactive Guide

Attackers don’t see your organization as a list of CVEs. They see a web of interconnected systems, looking for the path of least resistance to their target. They find one small weakness, then another, and chain them together to create a breach. So why would we defend our networks any differently?...

EUVD-2025-88355

Malicious code in toxicmousez3n npm...

Malicious code in toxic_lizard-smiletea (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 77334edd92072bf65b21d715217634f0f6241dfd3257b7faeeee14e9ed0801fc This package appears to be part of the tea.xyz token reward campaign that flooded npm. These packages typically contain autopublish scripts auto.js,...

MAL-2025-109792 Malicious code in toxic_goldfish_z3n (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 67120d9ad2e0243cb0f8ebe561a6f00c79d5484a85594b23b0f24f092b150dbc This package appears to be part of the tea.xyz token reward campaign that flooded npm. These packages typically contain autopublish scripts auto.js,...

EUVD-2025-78085

Malicious code in toxicgoldfishz3n npm...

EUVD-2025-78086

Malicious code in toxicbarracudaz3n npm...

Malicious code in toxic_goldfish_z3n (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 67120d9ad2e0243cb0f8ebe561a6f00c79d5484a85594b23b0f24f092b150dbc This package appears to be part of the tea.xyz token reward campaign that flooded npm. These packages typically contain autopublish scripts auto.js,...

EUVD-2025-83949

Malicious code in toxicparrotz3n npm...

EUVD-2025-83950

Malicious code in toxicchickadeez3n npm...

EUVD-2025-73245

Malicious code in toxicwhitefishrequirement npm...

EUVD-2025-73248

Malicious code in toxicduckz3n npm...

EUVD-2025-73247

Malicious code in toxicsailfishz3n npm...

MAL-2025-81749 Malicious code in toxic_jackal_z3n (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector f8cf3b490566601eeb7d1f0073611e724da78c4da18122d748434111303f4e81 This package appears to be part of the tea.xyz token reward campaign that flooded npm. These packages typically contain autopublish scripts auto.js,...

EUVD-2025-51480

Malicious code in toxic-amber-trout npm...

EUVD-2025-51479

Malicious code in toxic-brown-caterpillar npm...

EUVD-2025-56982

Malicious code in toxicmarsupialz3n npm...

LOKI: Proactively Discovering Online Scam Websites by Mining Toxic Search Queries

Online e-commerce scams, ranging from shopping scams to pet scams, globally cause millions of dollars in financial damage every year. In response, the security community has developed highly accurate detection systems able to determine if a website is fraudulent. However, finding candidate scam...

Malicious code in @malware-test-toxic-cubeb/test-mlw3-toxic-cubeb (npm)

The package @malware-test-toxic-cubeb/test-mlw3-toxic-cubeb was found to contain malicious code...