How indirect prompt injection attacks on AI work - and 6 ways to shut them down

Cybercriminals are tricking AI into leaking your data, executing code, and sending you to malicious sites. Here's how.
GitHub

Claude Code Skills & Plugins — Agent Skills for Every Coding Tool

235 production-ready Claude Code skills, plugins, and agent skills for 12 AI coding tools. The most comprehensive open-source library of Claude Code skills and agent plugins — also works with OpenAI ...
IEEE

Adversarial Example Generation and Detection Method Based on Black-box Query

Abstract: Deep learning models have been equally successful in other fields such as computer vision, natural language processing and self-driving. However, precision and high vulnerability of deep ...
the-decoder

LLMs crush coding and math but choke on casual questions, and that's not a contradiction

AI models can solve complex programming tasks in hours but fall apart when faced with basic everyday questions. Andrej Karpathy explains why that's not actually a contradiction. There are two ...
TMCnet

Symmetry Systems Expands Platform Capabilities with Symmetry AIGuard Enhancements, Million-Node Graph Visualization, and Claude Code Integration

SAN MATEO, Calif., April 9, 2026 /PRNewswire/ -- Symmetry Systems, the Data+AI security company, today announced a series of new and expanded capabilities in its quarterly platform update that give ...
GitHub

Pharmaceutical Supply Chain Demo

Tracing product flow Analyzing supplier dependencies Tracking supplier risks and dependency chains Understanding APIs (Active Pharmaceutical Ingredient) dependencies and connections Identifying risks ...