Skip to content
View Varshith-Kali's full-sized avatar
:octocat:
:octocat:
2 followers · 1 following

Achievements

Achievement: Pull SharkAchievement: Quickdraw

Achievements

Achievement: Pull SharkAchievement: Quickdraw

Block or report Varshith-Kali

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.

Content in all repositories owned by your account will be closed.
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
Varshith-Kali/README.md

Varshith Puli

Building the security layer for AI agents, LLM applications, and multi-agent systems. Active open-source contributor across AI Security, MCP/Agentic Security, DevSecOps, and Multi-Agent Systems.

LinkedIn Email

Focus Areas

  • AI Security & Red-Teaming — LLM vulnerability assessment, jailbreak detection, probe development
  • MCP / Agentic Security — Model Context Protocol security scanning, credential detection, tool poisoning
  • DevSecOps — SAST rule development, dependency hardening, CI/CD security
  • Multi-Agent Systems — Secure agent orchestration, guardrails, observability

Open Source Contributions

Repository Contribution PR Status
SyedAnas01/mcp-safeguard Replicate + Cohere API token detection (CRED-027, CRED-028) #8 Landed on main (ef6e9e6)
NVIDIA/garak AART probe for AI-assisted red-teaming across diverse cultural contexts #1974 Open — awaiting maintainer review
PyCQA/bandit Flask send_file() path traversal detection plugin #1459 Closed — resubmission in progress
trailofbits/mcp-context-protector Typed exception hierarchy (9 classes, backward-compatible) #55 Closed — resubmission in progress
microsoft/autogen MessageFilterAgent chronological ordering fix #7981 Closed — resubmission in progress
vibrantlabsai/ragas NonLLMContextRecall threshold + FactualCorrectness recall fix #2867, #2868 Closed — combining into one PR
google/adk-python OpenTelemetry dependency upper bound #6426 Closed — not pursuing
guardrails-ai/guardrails Typing modernization (validator_service) #1581 Closed — not pursuing
splx-ai/agentic-radar Rich dependency upper bound #131 Closed — not pursuing
NVIDIA/garak Transient HTTP error retry in OpenAICompatible #1973 Closed — withdrawn

Technical Skills

Languages: Python (primary), C++, JavaScript, TypeScript, SQL AI/ML: PyTorch, TensorFlow, scikit-learn, NumPy, Pandas, LangChain, LangGraph Security: Garak, Bandit, Semgrep, MCP security scanning, OWASP Top 10 for LLM & Agentic AI Infrastructure: Docker, Git/GitHub, FastAPI, MongoDB, MySQL, CI/CD, GitHub Actions

GitHub Stats

stats top-langs

Open to collaboration on AI security tooling, MCP security research, and multi-agent system hardening.

Popular repositories Loading

  1. Newsletter_Automation Newsletter_Automation Public

    TypeScript 1

  2. ThreatModelerX ThreatModelerX Public

    ThreatModelerX is a local-first Application Security automation platform that performs threat modeling, secure code scanning, and vulnerability visualization. It integrates Semgrep, Bandit, and Ret…

    Python 1

  3. Varshith-Kali Varshith-Kali Public

    Config files for my GitHub profile.

  4. Cli-Calc Cli-Calc Public archive

    Simple Calculator using C Program

    C

  5. Sample-Web-Project Sample-Web-Project Public archive

    Website which displays a pizza and provide options to add toppings on it !!!

    HTML

  6. face_recognition face_recognition Public

    Python