Author name: admin

This video explains the new LM Report AI Feature

This video explains the new AI HTTP Analyzer AI Feature

This video explains the new Shadow Repeater AI Feature

This video explains the new Finding broken access control with AI Feature

This video explains the new Record login sequence with AI Feature

This video explains the new Burp AI Explainer Feature

This video explains the new Burp AI Explore Feature

The J2 Playground by Scale AI is an interactive platform designed to test the resilience of large language models (LLMs)

Tensor Trust is an online game developed by researchers at UC Berkeley to study prompt injection vulnerabilities in AI systems.

PromptMap is a specialized LLM security scanner designed to detect and analyze prompt leaks—instances where a model inadvertently exposes hidden system

The Garak LLM vulnerability scanner is an open-source tool developed by NVIDIA to assess security risks in large language models

Prompt injection threats in terminals and IDEs via ANSI escape characters exploit the ability of these sequences to manipulate text

When AI agents autonomously browse websites and encounter tasks that are intentionally unsolvable or computationally intensive, they become susceptible to

AI agents that autonomously browse the web introduce significant security risks, particularly related to data exfiltration through covert copy-and-paste operations

Unbounded Consumption refers to scenarios where Large Language Models (LLMs) are subjected to excessive and uncontrolled usage, leading to resource

Misinformation refers to the generation of false or misleading information by Large Language Models (LLMs), which, despite appearing credible, can

Vector and Embedding Weaknesses refers to security vulnerabilities in Large Language Models (LLMs) that arise from improper handling of vector

System Prompt Leakage refers to the risk that system prompts—internal instructions guiding the behavior of Large Language Models (LLMs)—may inadvertently

Excessive Agency refers to the vulnerability arising when Large Language Models (LLMs) are granted more functionality, permissions, or autonomy than