# Ethical Kunsh

Ethical Kunsh is a remote worker on Himalayas, AI Security Red Team Expert at Alice.io, based in India.

Source: https://himalayas.app/@ethicalkunsh

```text
AI security researcher at Alice.io building agentic security evaluations and autonomous bug-bounty systems.
```

| Detail | Value |
| --- | --- |
| Availability | Looking for a job |
| Location | India |
| Authorized to work in | India |
| Salary expectations | 180k+ USD |
| Job categories | AI Safety and Security Researcher, Cybersecurity Researcher, Penetration Tester, Red Team Expert |
| Skills | AI Security, Adversarial Evaluation, AI Security Agents, Multi Agent Systems, Prompt Injection Testing, Offensive Security, Penetration Testing, Bug Bounty Hunting, Reconnaissance, Fuzz Testing, Exploit Validation, Authenticated Testing, Unauthenticated Attack Surface Testing, SOC Alert Triage, SIEM |
| Website | https://etxcyberops.etxhuman.com |
| LinkedIn | https://linkedin.com/in/ethicxlhuman-etxcyberops |
| GitHub | https://github.com/ethicxlhuman |
| Twitter | https://x.com/ethicxlhuman |

## About

```text
At Alice.io, I design adversarial security evaluation environments and indirect prompt-injection scenarios for agentic AI systems, testing whether they can be manipulated into policy-violating behavior. I build and validate agentic evaluations using deterministic checks and LLM-judged rubrics.

Through my independent research, I built DragonGate, an autonomous security research system spanning 350+ bug-bounty programs, and earned $4K+ in autonomous bounty rewards. At ETXcyberops, I built AI blue-team automations and am developing a managed continuous external penetration-testing service; both remain at the prototype or development stage.
```

## Experience

### AI Security Red Team Expert (current)

Alice.io. Sep 2026 - Present

```text
Design adversarial security evaluation environments and indirect prompt-injection scenarios for agentic AI systems. Build and validate agentic/RL-gym evaluations using deterministic checks and LLM-judged rubrics.
```

Skills: Adversarial-Evaluation, Prompt-Injection, Agentic-AI, RL-Gym, AI-Evaluation-Rubrics

### Founder (current)

ETXcyberops. Aug 2025 - Present

```text
Building AI blue-team automations and a managed continuous external penetration-testing service. Designed the find → prove → report workflow with written scope, reproducible evidence, and auditable testing.
```

Skills: AI-Security-Automation, SIEM-Alert-Triage, Penetration-Testing, Workflow-Design

### Independent Cybersecurity Researcher (current)

Autonomous Security Research & Bug Bounty. Jan 2023 - Present

```text
Identified and responsibly disclosed vulnerabilities across major platforms, earning $12K+ in bug bounties. Built DragonGate, a three-layer autonomous security research system, and studied agent oversight, reward hacking, and sandbagging.
```

Skills: Bug-Bounty, Vulnerability-Research, LLM-Agents, Multi-Agent-Systems, Autonomous-Security

## Education

### University of Mysore

Bachelor of Computer Applications, Computer Applications. 2023 - 2026. Grade: CGPA 7.8

```text
Pursued a Bachelor of Computer Applications (BCA) from 2023 to 2026, achieving a CGPA of 7.8.
```

### INE

eJPTv2, Penetration Testing

```text
Earned the eJPTv2 certification from eLearnSecurity (INE).
```

## Tech stack

- PostgreSQL
- React
- Python
- Linux
- TypeScript
- Supabase
- Playwright
- N8N

To contact Ethical, message them from this profile with a Himalayas employer account: [Hire on Himalayas](https://himalayas.app/hire).

## People also viewed

- [Mayukh Dey](https://himalayas.app/@mayukhdey): AI Security Specialist, Independent / Personal Projects
- [Avash Pati](https://himalayas.app/@avashpati): PortSwigger Web Security Academy, PortSwigger
- [Parth Bhatt](https://himalayas.app/@parthbhatt3): Cyber Security Intern, DRDO (SAG), Ministry of Defence
- [maheswari kota](https://himalayas.app/@maheswarikota): Senior Executive, Softenger (I) Private Limited
- [Mir Arsalan](https://himalayas.app/@mirarsalan): Independent Cybersecurity Researcher, Self Directed
- [Uday Pali](https://himalayas.app/@udaypali): Independent Security Researcher, Self Employed
- [M S Aditya](https://himalayas.app/@msaditya): Security Research Intern, CERT IN
- [DEBRAJ BASAK](https://himalayas.app/@debrajbasak): Senior Security Researcher, Trellix
- [Ranjith Ashok](https://himalayas.app/@ranjithashok): Cyber Defense and Incident Response Analyst, KPMG
- [Shubham Pundir](https://himalayas.app/@shubhampundir1): Security Engineer & DevOps, Aventior
