🍥

记录并分享日常

Tags

17 pages

Cybersecurity

How Destructive Command Guard protects Codex: intercepts dangerous Git and Shell commands

OpenAI's AI Hacked Hugging Face to Cheat on a Test

Is AI Agent automated penetration testing legal? Authorization boundaries, Strix-style tools, and compliance checklist

Strix Introduction: Using AI Agents for Automated Penetration Testing and Vulnerability Remediation

Claude Fable 5 Returns Globally: How Anthropic Addressed the Model Jailbreak Controversy

Anthropic Suspends Fable 5 and Mythos 5 Over Security Concerns

How to Handle the HTTP/2 Bomb Vulnerability: Impact and Mitigation for CVE-2026-49975

Claude Fable 5 and Mythos 5 Released: Anthropic Brings Mythos-Class Capabilities to Regular Users

poc-lab Patch Verification: Confirm Whether Recent High-Severity Vulnerabilities Are Fixed, Including Chrome CSSFontFeatureValuesMap UAF, NGINX Rift, Dirty Frag, and Fragnesia

APT45 Uses AI to Validate Vulnerabilities at Scale: The Barrier to Zero-Day Attacks Is Falling

Do Not Push API Keys to GitHub: A Secret-Leak Prevention Guide for AI Coding

How to Check CVE-2026-42945: Nginx Rift Trigger Conditions, Version Checks, and Upgrade Advice

Claude Mythos Preview: Why Anthropic Put Its Strongest Cybersecurity Model Inside Project Glasswing

May 2026 Edge High-Risk Vulnerability CVE-2026-2441: Malicious Pages May Trigger Remote Code Execution

Copy Fail CVE-2026-31431: Container Escape Risk in the Linux Kernel File-Copy Path

OpenAI Introduces Advanced Account Security: A Stronger Layer of Protection for ChatGPT and Codex Accounts

hackingtool: Uses, Risks, and Learning Boundaries of an All-in-One Security Toolkit