AI Security Research

Miller Engelbrecht Security Research

Finding the cracks in AI systems before they become someone else's exploit.

Top 5
0din.ai Leaderboard
40+
Bugs Found & Awarded
HackerOne
Active Researcher
0D 0din.ai Profile in LinkedIn
Writing
How I Engineered a Closed-Loop AI Red-Teaming Research Harness ↗
June 5, 2026 ai-security red-team
Clone This Repo and I Own Your Machine ↗
May 21, 2026 ai-security bug-bounty 0din.ai
as seen in BleepingComputer SecurityWeek Tom's Hardware SANS ISC +68 more
0din.ai Submissions
Guardrail Jailbreaks via Contextual Reframing
20+ submissions
Content safety filter bypasses across multiple frontier AI models using prompt reframing tactics: academic chemistry, forensic training scenarios, pharmaceutical analysis, verbose simulation, patent litigation framing, and incremental escalation patterns. Each variant bypasses model-level guardrails without triggering refusal heuristics.
ai-safety multiple models 0din.ai
Indirect Prompt Injection via Embedded Content
multiple submissions
Data exfiltration through indirect prompt injection in AI-powered applications that process external content: email clients, document readers, and web browsing agents. Injected instructions embedded in legitimate-looking content redirect agent behavior to leak conversation context or user data.
prompt-injection exfiltration 0din.ai
Agentic Attack Surfaces in AI Coding Tools
multiple submissions
Attack chains targeting AI coding agents through workspace configuration files, package manager lifecycle hooks, and git repository metadata. Includes DNS-controlled payload delivery via npm postinstall, invisible Unicode injection in commit messages, and AGENTS.md trust exploitation.
ai-security coding-agents 0din.ai