autoguardrails

autoguardrails Santander AI Lab의 오픈 소스입니다. LLM/AI 안전 가드레일 연구 라이브러리/평가 하네스autoresearch 스타일입니다: 단일 변경 가능한 policy.md 표면을 검색하여 고정된 평가 스위트에 대한 공격 성공률ASR을 최소화하고, 무해 통과 기준benign-pass floor이 있습니다. Santander AI Open Source의 일부 — Banco Santander의 오픈 소스 AI 프로젝트 santander.com입니다. autoguardrails는 Karpathy의...

EUVD-2026-37607

Unauthenticated PHP Object Injection in AI Lab 5.4.2 versions...

CVE-2026-42380

Unauthenticated PHP Object Injection in AI Lab 5.4.2 versions...

CVE-2026-42380 WordPress AI Lab theme < 5.4.2 - PHP Object Injection vulnerability

Unauthenticated PHP Object Injection in AI Lab 5.4.2 versions...

CVE-2026-42380 WordPress AI Lab theme < 5.4.2 - PHP Object Injection vulnerability

Unauthenticated PHP Object Injection in AI Lab 5.4.2 versions...

CVE-2026-42380

CVE-2026-42380 covers the WordPress AI Lab theme prior to version 5.4.2, which is vulnerable to unauthenticated PHP Object Injection. The Patchstack entry and CVE records indicate the vulnerability is fixed in 5.4.2. Impact is high (remote, unauthenticated) per the CVSS vector: Network, None priv...

CVE-2026-42380: Deserialization of Untrusted Data

Unauthenticated PHP Object Injection in AI Lab 5.4.2 versions...

PT-2026-50326

Unauthenticated PHP Object Injection in AI Lab 5.4.2 versions...

WordPress AI Lab theme < 5.4.2 - PHP Object Injection vulnerability

PHP Object Injection vulnerability discovered by Tran Nguyen Bao Khanh VCI - VNPT Cyber Immunity in WordPress Theme AI Lab versions 5.4.2...

Bitcoin Forensic Analysis Uncovers Money Laundering Clusters and Criminal Proceeds

A forensic analysis of a graph dataset containing transactions on the Bitcoin blockchain has revealed clusters associated with illicit activity and money laundering, including detecting criminal proceeds sent to a crypto exchange and previously unknown wallets belonging to a Russian darknet marke...