Offensive
security
research
By Jihwan yoon (blackcon) — exploit development, reversing, and vulnerability research on AI systems, hypervisors, and the things people trust. Recent work includes a critical LiteLLM RCE (silently patched before a planned Pwn2Own 2026 entry) and a Claude Code trust-model analysis disclosed through HackerOne.
Featured research
-
Claude Code의 trust prompt 우회 3종 — HackerOne 제보와 "intended behavior" 종결
Three independent ways to bypass Claude Code's trust prompt for silent shell execution from a cloned repo — and why Anthropic closed all three as intended be...
-
LiteLLM에서 발견한 Jinja2 SSTI 취약점 — Pwn2Own 2026 출전 시도와 silent fix 분석
A single unauthenticated request reached uid=0 on the LiteLLM proxy via Jinja2 SSTI — a critical RCE silently patched days before a planned Pwn2Own Berlin 20...
-
MCP 보안 취약점, Advanced-Tool-Poison-Attack
Advanced Tool Poisoning hides malicious instructions in MCP tool outputs rather than descriptions, defeating defenses that only inspect tool metadata.
-
HVFUZZ
A Hyper-V hypercall fuzzer built on hAFL2 for hunting bugs in the Microsoft virtualization stack.