avatar
blackcon
Offensive security research
  • HOME
  • ABOUT
  • BLOG
  • PROJECTS
  • CAREER
  • CATEGORIES
  • ARCHIVES
  • TAGS
Home
blackcon
Cancel

Offensive Security Research

Exploit development,
reversing & vulnerability
research.

Jihwan yoon(blackcon)의 연구 공간. AI/LLM 인프라와 가상화 스택을 파고듭니다. 최신 작업은 아래 색인에서 확인하세요.

Featured research 11 entries
  1. 01 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 c... Research · AI-Security — 2026.05.12
  2. 02 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 befo... Research · AI-Security — 2026.05.03
  3. 03 MCP 보안 취약점, Advanced-Tool-Poison-Attack Advanced Tool Poisoning hides malicious instructions in MCP tool outputs rather than descriptions, defeating defenses that only... Research · MCP — 2025.04.10
  4. 04 MCP 보안 취약점, Tool-Poison-Attack How Tool Poisoning hides malicious instructions inside MCP tool descriptions to manipulate the LLM that consumes them. Research · MCP — 2025.04.10
  5. 05 HVFUZZ A Hyper-V hypercall fuzzer built on hAFL2 for hunting bugs in the Microsoft virtualization stack. Research · Hyper-v — 2022.03.29
Latest View all →
  1. 01 Claude Code의 trust prompt 우회 3종 — HackerOne 제보와 "intended behavior" 종결 Research — 2026.05.12
  2. 02 LiteLLM에서 발견한 Jinja2 SSTI 취약점 — Pwn2Own 2026 출전 시도와 silent fix 분석 Research — 2026.05.03
  3. 03 MCP 보안 취약점, Advanced-Tool-Poison-Attack Research — 2025.04.10
  4. 04 MCP 보안 취약점, Tool-Poison-Attack Research — 2025.04.10
  5. 05 CTF 문제로 알아보는 ESP32 리버싱 Hacking — 2025.03.31
  6. 06 ROP (Return Oriented Programming) 란? Hacking — 2024.12.21
Trending Tags
Hacking System hacking AI hacking research basic disclosure programming python aptos

© 2026 blackcon. Some rights reserved.

Powered by Jekyll with Chirpy theme.

Trending Tags
Hacking System hacking AI hacking research basic disclosure programming python aptos

A new version of content is available.