Author: Mamta Upadhyay

When language models interact, even safe ones can amplify hidden threats

Learn how to build a lightweight AI agent using a local LLM and simple tools

Feedback loops in AI agents can be silently exploited to manipulate behavior over time without ever touching the prompt.

How memory poisoning and tool access in open-source agents can silently lead to critical security breaches

Context flooding aka Cognitive Overload does not cause immediate failures skews the agent’s decision making

A simple, context-aware QA bot that runs locally or with OpenAI. Perfect for beginners exploring LLM builds and RAG workflows.

Demo to explore how AI agents can be manipulated to misuse tools

What would you target first in a prompt pipeline that scrapes the web?

MCP architectures create hidden pathways for LLM compromise

Understanding the Critical Divide in Responsible AI