Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings
@ni5h4nt
ni5h4nt
Follow

Nishant Tyagi ni5h4nt

Highlights

  • Pro

Block or report ni5h4nt

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 is supported. This note will only be visible to you.
Report abuse

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

Report abuse
ni5h4nt /README.md

Nishant Tyagi

Nishant Tyagi · Cybersecurity · AI Security · Agentic Systems

Cybersecurity · AI Security · Agentic Systems

Cybersecurity engineer, independent researcher, and inventor working at the intersection of AI security, detection engineering, and agentic systems.

I build security infrastructure for complex systems: intrusion prevention, phishing detection, cloud-scale platforms, AI security controls, and guardrails for LLM and agentic workflows. I have 20+ years of experience across cybersecurity, infrastructure, applied AI, and secure platform architecture.

cybertect.ai · LinkedIn · ORCID

What I Build

Open source

sigmalint · ESLint-style linter for Sigma detection rules, with deterministic quality checks for maintainability, metadata hygiene, logic structure, and platform portability. MIT licensed, available on PyPI, and citable via DOI.

prompt-injection-scanner · Defensive tool for detecting prompt injection attacks in LLM applications. Multi-stage pipeline (heuristics, vector similarity, LLM guardian) with structured-output policy guardrails.

Upstream · Machine-readable per-rule changelog for the Sigma standard: SigmaHQ/sigma #6050.

Research

Background

  • 20+ years in founding and principal engineering roles, building complex systems across security, infrastructure, and applied AI
  • Hands-on across intrusion detection and prevention engines, AI-driven phishing defense, cloud-scale detection platforms, and runtime guardrails for LLM and agentic workflows
  • Carnegie Mellon University, MS Information Technology, Information Security (2013) · MIT Professional Education, Applied Data Science (2023) · CISSP

Writing

Latest from cybertect.ai:

Also: 30 system design walkthroughs with Mermaid architecture diagrams.

Popular repositories Loading

  1. sigmalint sigmalint Public

    ESLint-style linter for Sigma detection rules. Validates against Sigma 2.1.0, scores rules across six quality dimensions, emits stable rule IDs.

    Python 26 10

  2. code-review code-review Public

    AI-powered desktop code review assistant: multi-provider LLM support, Temporal workflows, tree-sitter semantic indexing, vector search, privacy-first.

    Python 1

  3. system-design system-design Public

    30 system design interview walkthroughs with Mermaid architecture diagrams — by Nishant Tyagi

    HTML 1

  4. aws-sso-cred-manager aws-sso-cred-manager Public

    The AWS SSO Credential Manager is a Python script that helps manage AWS Single Sign-On

    Python

  5. prompt-injection-scanner prompt-injection-scanner Public

    A defensive security tool for detecting prompt injection attacks in LLM applications. Multi-stage pipeline (heuristics → vector similarity → LLM guardian) with structured-output policy guardrails.

    Python

  6. agentic-coding-tutorials agentic-coding-tutorials Public

    Hands-on tutorials for building software with AI coding agents like Claude Code.

    HTML

AltStyle によって変換されたページ (->オリジナル) /