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.
ai Security Research
17 articles in this topic.
August 2026
1 article- 10 min read
March 2026
9 articles- 30 min read
WP Google Map Plugin - Three Weak Links, One Critical Chain
Line 781 says $query_to_run is safe. It isn't. An autonomous pipeline found a CVSS 9.8 unauthenticated SQL injection in WP Google Map Plugin v4.9.1 -- a three-link chain of individually harmless components that, together, give any visitor full database access. Then we kept reading and found the plugin deserializes update-check responses from an external server with maybe_unserialize(). 200,000+ active installs. 35 minutes. $8.97.
- 24 min read
CVE-2026-4105: systemd-machined Privilege Escalation - 72 Minutes from Drop to Bypass
CVE-2026-4105 dropped this morning - local privilege escalation to root on desktop Linux via systemd-machined. Two D-Bus calls, no authentication. We fed it to CVEForge before the advisory was an hour old. Seventy-two minutes later: confirmed exploit, Docker labs for vulnerable and patched builds, and a bypass proving the vendor's fix is incomplete. The analysis agent said the fix was thorough. The bypass agent proved it wrong.
- 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
7 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.
- 7 min read
Anatomy of a Trojan Exploit - How We Detect Backdoored PoCs with AI
Concrete examples of credential stealers, obfuscated backdoors, and destructive payloads found in public PoC material, with model interpretation kept separate from EIP safety claims.