---
id: 8635
title: "[CVE-2024-6100] CyberKimi Benchmarks: Autonomous Exploitation Traces & Evidence"
cve: CVE-2024-6100
source_domain: github.com
source_url: "https://github.com/lordx64/cyberkimi-benchmarks"
published_at: "2026-08-09T15:35:56Z"
tags: ["ai-security", "rce", "benchmark", "github", "red-team", "cve", "autonomous-exploitation"]
phying_url: "https://phying.com/item/8635"
lang: en
---

# [CVE-2024-6100] CyberKimi Benchmarks: Autonomous Exploitation Traces & Evidence

## Summary

Open benchmarks and raw audit evidence demonstrating the autonomous offensive capabilities of CyberKimi (a cyber-tuned Kimi K3 with refusal ablation). The repository contains detailed evaluation results and wire transcripts for CyberGym (solving 78/90 production crash reproduction tasks) and ExploitBench (achieving 16/16 on a multi-stage V8 CVE-2024-6100 exploitation ladder to full arbitrary code execution), accompanied by rigorous anti-contamination analysis.

## Why it matters

Provides verifiable, transparent evidence of advanced LLMs performing complex, multi-step binary and browser exploitation autonomously under strict ASLR and memory randomization defenses.

## Intelligence Metadata

- **Sources:** github.com
- **CVE:** CVE-2024-6100
- **Published:** 2026-08-09T15:35:56Z
- **Original:** https://github.com/lordx64/cyberkimi-benchmarks
- **Phying News:** https://phying.com/item/8635