Cassius Oldenburg

AI Red Teamer

This is what I do for fun. It'd be cool to do it for work too.

Hack-a-Prompt 2.0 Leaderboard showing 1st place

Hack-a-Prompt 2.0 Final Leaderboard, September 2025

Competition Results

Hack-a-Prompt 2.0

1st Place, Team RED_CORE

MATS x TRAILS competition. Indirect prompt injection against AI agents with real tool access. Broke all six frontier models.

Full writeup with execution logs

Gray Swan Arena

#22 Proving Grounds, #32 Indirect Prompt Injection

300+ breaks across 40+ behaviors. Bypassed "untrusted web content" defenses, exploited subagent architectures.

Projects

RED_CORE

Multi-model, multi-turn prompt testing framework. 27+ models across 8 providers, dual evaluation (regex + LLM-as-judge), CLI for experiment orchestration.

github.com/RED-BASE/RED_CORE

Claude Poker

MCP server that lets Claude play poker using computer vision. Screen capture, card recognition, game state tracking.

github.com/RED-BASE/claude-poker

Available for red teaming roles and research collaborations.