Auto Exploit LLM-assisted exploit generation research
Technical Analysis
Summary
Hide ▲
Show ▼
Researchers built Auto Exploit, an AI-driven system that generated proof-of-concept exploits for 14 open source vulnerabilities in as little as 15 minutes, compressing defender response assumptions. The work shows LLM-assisted exploit generation can move from research to practical turnaround at machine speed. That speed shifts priority toward reachability analysis and rapid patching rather than waiting on traditional exploitability judgments.
Related Happenings
Anthropic launches Claude Opus 4.6 with code review and vulnerability-finding capabilities
Security Tool/Service
First: 06.02.2026 07:49
Last: 06.02.2026 07:49
Sources 1
About this happening:
**Anthropic** launched **Claude Opus 4.6** with stronger **code review** and **debugging** support, and the model has already been used to uncover **more than 500** previously unk...
Anthropic launches Claude Opus 4.6 with code review and vulnerability-finding capabilities
Security Tool/ServiceAbout this happening: **Anthropic** launched **Claude Opus 4.6** with stronger **code review** and **debugging** support, and the model has already been used to uncover **more than 500** previously unk...
AI-powered IDEs prompt-injection RCE and data-exfiltration flaws (multiple vulnerabilities)
Vulnerability
First: 06.12.2025 17:24
Last: 06.12.2025 17:24
Sources 1
About this happening:
A disclosed set of **30+ vulnerabilities** in **AI-powered IDEs and coding assistants** creates **data exfiltration** and **remote code execution** risk across tools such as **Cur...
AI-powered IDEs prompt-injection RCE and data-exfiltration flaws (multiple vulnerabilities)
VulnerabilityAbout this happening: A disclosed set of **30+ vulnerabilities** in **AI-powered IDEs and coding assistants** creates **data exfiltration** and **remote code execution** risk across tools such as **Cur...
B3 open-source benchmark for backbone LLM security
Security Tool/Service
First: 29.10.2025 12:45
Last: 29.10.2025 12:45
Sources 1
About this happening:
**AISI**, **Check Point**, and **Lakera** released **b3**, an open source benchmark that helps developers measure how well **backbone LLMs** resist prompt manipulation and other a...
B3 open-source benchmark for backbone LLM security
Security Tool/ServiceAbout this happening: **AISI**, **Check Point**, and **Lakera** released **b3**, an open source benchmark that helps developers measure how well **backbone LLMs** resist prompt manipulation and other a...
Dassault Systèmes DELMIA Apriso and XWiki active exploitation wave
Exploitation Wave
First: 29.10.2025 09:44
Last: 29.10.2025 09:44
Sources 1
About this happening:
**CISA** and **VulnCheck** say **DELMIA Apriso** and **XWiki** flaws are being exploited in the wild, expanding risk across multiple products and CVEs. The abuse can lead to **arb...
Dassault Systèmes DELMIA Apriso and XWiki active exploitation wave
Exploitation WaveAbout this happening: **CISA** and **VulnCheck** say **DELMIA Apriso** and **XWiki** flaws are being exploited in the wild, expanding risk across multiple products and CVEs. The abuse can lead to **arb...
TEE.Fail DDR5 side-channel analysis of Intel TDX and AMD SEV-SNP memory interposition
Technical Analysis
First: 28.10.2025 21:16
Last: 28.10.2025 21:16
Sources 1
About this happening:
**TEE.Fail** is a newly demonstrated **DDR5** side-channel that can extract secrets from **Intel SGX/TDX** and **AMD SEV-SNP**, weakening trust in confidential-computing attestati...
TEE.Fail DDR5 side-channel analysis of Intel TDX and AMD SEV-SNP memory interposition
Technical AnalysisAbout this happening: **TEE.Fail** is a newly demonstrated **DDR5** side-channel that can extract secrets from **Intel SGX/TDX** and **AMD SEV-SNP**, weakening trust in confidential-computing attestati...
Timeline
-
29.08.2025 16:01 2 articles · 9mo ago
Auto Exploit generates proof-of-concept exploits for 14 open source vulnerabilities
Technical Analysis UpdateTwo Israeli cybersecurity researchers built Auto Exploit, an AI-powered offensive research system that uses LLM prompts, CVE advisories, and patches from open source repositories to generate and validate proof-of-concept exploit code. The analysis pipeline uses Anthropic's Claude-sonnet-4.0 model to analyze advisories and code patches, create a vulnerable test application, and test the results against vulnerable and patched versions of the target application, with some exploits produced in as little as 15 minutes.
Show sources
- Proof-of-Concept in 15 Minutes? AI Turbocharges Exploitation — www.darkreading.com — 29.08.2025 16:01
- Proof-of-Concept in 15 Minutes? AI Turbocharges Exploitation — www.darkreading.com — 29.08.2025 16:01