Skip to content
View HPBhoir's full-sized avatar
  • Michigan, USA

Block or report HPBhoir

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
HPBhoir/README.md

Hi, I'm Harshal Bhoir

I'm a software engineer with a background in AI and cybersecurity, focused on building secure AI systems, evaluating LLM applications, and researching AI agent security.

Current Focus

  • AI Agent Security
  • LLM Security
  • AI Governance
  • Application Security

Featured Projects

  • 🚀 AgentSecBench
    Open-source framework for evaluating the security of tool-using AI agents.

  • 🛡️ Secure RAG Red Team Lab
    Hands-on AI security project demonstrating attacks and defenses for Retrieval-Augmented Generation systems.

Technical Skills

Python • LLM Security • RAG • LangChain • Prompt Injection • Threat Modeling • Application Security • Machine Learning • Git • Docker

Currently Learning

  • Agent security evaluation
  • AI governance
  • Secure AI system design

Connect

Pinned Loading

  1. AgentSecBench AgentSecBench Public

    Open-source framework for evaluating the security of tool-using AI agents.

    Python

  2. secure-rag-redteam-lab secure-rag-redteam-lab Public

    A hands-on AI security project demonstrating prompt injection, data exfiltration, and defense strategies in Retrieval-Augmented Generation (RAG) systems.

    Python 1