EIP v3: The Exploit Database We Meant to Build
EIP v3 is a rebuilt exploit intelligence system with searchable PoC code, a public read-only API, CLI and MCP, and a review-gated Kimi/Ollama pipeline that publishes CVE labs into the corpus.
mcp Security Research
15 articles in this topic.
August 2026
1 article- 10 min read
May 2026
1 article- 27 min read
Hermes Agent with EIP Harness: The Vulnerability Research Assistant That Also Runs Your Pipelines
Hermes Agent with the EIP Harness: a conversational AI vulnerability research assistant that runs full CVE pipelines while you stay in the loop. Built on Nous Research's Hermes. Showcase: a GitLab runner-token leak chained to RCE (CVE-2022-0735), a neatvnc pre-auth stack overflow (CVE-2026-42859), and a KEV-listed Everest Forms PHP Object Injection (CVE-2026-3296), all end to end. Our first public release of EIP CVE pipeline craft, plus win11-forge for Windows kernel and usermode lab orchestration.
March 2026
7 articles- 12 min read
CVE-2026-28391: OpenClaw Command Injection - The Day I Hacked Myself
CVE-2026-28391 is a CVSS 9.8 command injection in OpenClaw < 2026.2.2, caused by a POSIX vs cmd.exe shell-parsing mismatch. Our own suggestion algorithm ranked it as the most interesting CVEForge target. 8/8 bypass vectors confirmed, code execution verified. This is the story of the day our orchestration layer dispatched a full vulnerability assessment against itself.
- 20 min read
Introducing FuzzForge: Autonomous Source-Code Fuzzing - Finding Bugs in nginx in 112 Minutes
We forked Shannon a third time. Seven AI agents, source code as the starting point, sanitizer-instrumented builds, and a pipeline that read 259 C files, built its own fuzzing harnesses, ran 18,000 iterations, and found a previously unknown FastCGI protocol desynchronization bug in nginx. Two hours. Twenty-five dollars.
- 27 min read
CVE-2025-68670 Part 2: From Crash to RCE - The One That Fought Back (and Lost)
The first post ended with 'not a shell.' This one ends with uid=0(root) - with an asterisk. Ten context windows. A UTF-8 encoding barrier that blocks every libc address. A PLT mapping that lied. A stack alignment problem solved by a NULL pointer and a filename that shouldn't exist. The story of how a pre-auth xrdp overflow became (almost) pure-network RCE - through the most absurd gadget chain we've ever built.
- 10 min read
CVE-2025-68670: Pre-Auth xrdp Overflow - The One Where the Protocol Fought Back
xrdp. Pre-authentication. A full RDP handshake implemented from scratch. UTF-8 encoding constraints that break your ROP chain. A false crash path that wasted hours. And a 3-byte partial overwrite technique that reaches any address in the binary. Stackforge's hardest target yet - and the most honest result.
- 17 min read
CVE-2025-62507: Redis Stack Overflow to RCE in 68 Minutes - Then We Turned ASLR On
The public material available during this CVE-2025-62507 run was a crash PoC. StackForge pursued RCE, then repeated the work with ASLR enabled.
- 22 min read
CVE-2025-15467: From OpenSSL Stack Overflow to Three ROP Chains in 64 Minutes - Introducing Stackforge
We forked Shannon again - this time for binary exploit development. Nine AI agents, GDB as an MCP tool, packet capture via SharkMCP, and a pipeline that turned an OpenSSL stack buffer overflow into three independent ROP chains with GDB-verified RCE. Eighty-five minutes. Twenty-five dollars. Here's how Stackforge works.
- 28 min read
CVE-2025-26866: From Undocumented Binary Protocol to Root Shell - AI Agent Meets Java Deserialization
CVE-2025-26866 is a Hessian deserialization RCE in Apache HugeGraph PD. Our autonomous exploit pipeline CVEForge - which had completed 56 consecutive CVEs - hit a wall: an undocumented binary protocol, a non-standard serialization format, and a class blacklist blocking every known gadget chain. The agent spent $49 and four hours reverse-engineering SOFABolt, mapping sofa-hessian byte by byte, and finding a JDK-only gadget chain to bypass the blacklist. Then we took over to turn file creation into a proper root shell - navigating JNDI hardening, CC library defenses, and a gadget chain that silently dies on modern JDK. The result: a full Metasploit module.
February 2026
6 articles- 19 min read
72 Hours, 24 CVE Proof of Concept Exploits, and 8 Disclosure Submissions: The CVEForge Stress Test
We left CVEForge running for three days. Twenty-four CVEs went in. All twenty-four produced working PoCs. Ten incomplete fixes triggered eight responsible disclosure submissions - six GitHub issues, one MITRE report, one HackerOne 0-day. Here's the full accounting.
- 7 min read
CVE-2025-60355 (OneBlog): CVEForge Finds 3 Bypass/Incomplete Fixes in 5 CVE Runs
In this CVEForge patch-validation run, we analyze CVE-2025-60355 in OneBlog (Java/FreeMarker) and compare outcomes across five CVEs. Three of five runs ended in confirmed bypass or incomplete-fix results.
- 11 min read
Zero to RCE: Autonomous Exploit Development Across Three Vulnerability Classes
After CVEForge's first successful run, we needed to know if it was luck or a pattern. Two more CVEs, zero hand-holding, and an AI agent that found a fix bypass the developers missed.
- 10 min read
CVE-2025-53833: Autonomous PoC Generation with CVEForge - From CVE Number to Root Shell in 32 Minutes
We forked Shannon - the open-source AI pentesting framework - and wired it to the EIP MCP server. Six AI agents, one CVE number, 32 minutes: a working RCE PoC for a CVSS 10.0 vulnerability with zero existing public exploits. Here's how it happened.
- 10 min read
CVE-2026-28296: From CRLF Injection PoC to Fix Bypass - One Prompt, One AI Agent
One prompt kicked off an AI agent that built a full PoC lab for CVE-2026-28296 - and discovered the GVFS CRLF injection fix was incomplete. Here's how it happened.
- 5 min read
Introducing the EIP MCP Server - Vulnerability Intelligence for AI Assistants
The story behind EIP MCP, with current setup guidance: tell your agent to connect to the hosted endpoint, or install the optional local eip-mcp package through pipx.