Skip to content
View Hellsender01's full-sized avatar
413 followers · 0 following
  • Prescient Security
  • India

Achievements

Achievement: StarstruckAchievement: Pull SharkAchievement: Arctic Code Vault Contributor

Achievements

Achievement: StarstruckAchievement: Pull SharkAchievement: Arctic Code Vault Contributor

Organizations

@Red-Knights-CTF

Block or report Hellsender01

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
Hellsender01/README.md

Security researcher who enjoys poking at systems that were never meant to break.

Lately I have been spending most of my time exploring AI and LLM security. This includes prompt injection, agent based systems and red teaming language models.

What I am working on

  • LLMMap
    An automated prompt injection testing framework for LLM-integrated applications, inspired by sqlmap. Discovers injection points in HTTP requests, generates targeted payloads using a dual-LLM architecture and confirms findings with statistical reliability testing. Covers 227 prompt injection techniques across 18 attack families with support for Ollama, OpenAI, Anthropic and Google backends. LLMMap

  • Prompt Injection Taxonomy
    253 prompt injection techniques organized into 17 attack categories with mapping to the OWASP LLM Top 10.
    Prompt Injection Taxonomy

  • Researching attack surfaces in agent based AI systems and RAG pipelines

Pinned Loading

  1. LLMMap LLMMap Public

    Automated prompt injection testing framework for LLM-integrated applications with dual-LLM architecture.

    Python 1

  2. prompt-injection-taxonomy prompt-injection-taxonomy Public

    A structured reference covering 253 prompt injection techniques across 17 attack categories, 4 injection classes and the full OWASP LLM Top 10 threat surface.

    3 2

  3. PentesterPro PentesterPro Public

    Autonomous Pentesting System using Flask and LLMs.

    Python 4 2

  4. Red-Knights-CTF/writeups Red-Knights-CTF/writeups Public

    C 27 11