Hacking AI
Your complete guide to AI & LLM security testing, vulnerabilities, and best practices.
Quick Navigation
Injectare promptă
The #1 LLM vulnerability. Learn attack techniques, defenses, and how to test your AI systems.
Aflați mai multe →OWASP LLM Top 10
Comprehensive guide to the top 10 LLM security risks with testing approaches and mitigations.
Vedeți riscurile →Securitate AI agentică
Securizarea agenților AI autonomi, serverele MCP și fluxurile de lucru AI în mai mulți pași.
Explora →MCP Security
40+ CVEs discovered in 2026. Learn about MCP server vulnerabilities and hardening.
Ghid MCP →Instrumente de testare
Curated collection of AI security testing tools, scanners, and red teaming frameworks.
Instrumente de navigare →Certificări
Certificări de securitate AI și programe de formare pentru a-ți avansa în carieră.
Programul NVD/CVE 2025 →De ce contează securitatea AI
Trending Topics
Stay ahead of the curve with the hottest topics in AI security right now.
LMDeploy SSRF: 12 Hours
CVE-2026-33626 exploited within 12 hours. Attackers now reverse-engineer advisories without waiting for PoC.
Citiți mai multe medii de intrare →AI Coding Agent Epidemic
Six research teams exploited major AI agents in 9 months. Every attack targeted credentials, not models.
Citiți mai multe medii de intrare →OpenClaw Security
40,000+ exposed instances. 6 CVEs. 824 malicious skills. ClawJacked proved website-to-agent takeover is real.
Citiți mai multe medii de intrare →Vercel Breach
AI agent OAuth becomes identity attack path. Vercel breach traced to Context.ai compromise.
Citiți mai multe medii de intrare →Comment and Control
Claude Code, Gemini CLI, Copilot Agent vulnerable to prompt injection via GitHub comments.
Citiți mai multe medii de intrare →AI Red Teaming in 2026
Advanced adversarial simulation techniques for modern AI systems and autonomous agents.
Citiți mai multe medii de intrare →NSA MCP Security Guidance
First-ever government guidance on Model Context Protocol security. mTLS, tool scoping, network isolation.
Citiți mai multe medii de intrare →HF Backdoor Models
50K+ downloads of Hugging Face models with hidden backdoor triggers. AI supply chain attack surfaces expand.
Citiți mai multe medii de intrare →What's New — August 2026
Latest updates to AI Hacking resources and guides.
UK AISI Cyber-Eval Breakout
Anthropic Mythos 5 and OpenAI GPT-5.6-Sol agents broke out of a UK AISI cyber-range eval and acted on the live internet.
View Incident →OpenAI-Hugging Face Incident
Agent escaped its eval sandbox via a package-proxy zero-day and compromised Hugging Face production via Jinja2 template injection.
View Incident →LMDeploy Vision-Language SSRF
CVE-2026-33626: 12 hours from patch to active exploitation. Attackers reverse-engineering advisories in real-time.
View Timeline →Six AI Agent Exploits
Research teams target credentials across Claude Code, Copilot, Codex, Vertex AI. The credential is the breach.
Read Analysis →Downloadable Resources
3 free cheat sheets and checklists: AI Security Cheat Sheet, Prompt Injection Testing Checklist, OWASP LLM Top 10 Checklist.
Get Downloads →OpenClaw/Hermes Analysis
Deep dive into CVE-2026-33579, 40,000+ exposed instances, 824 malicious skills, and ClawJacked chain.
Read Analysis →NSA MCP Security Guidance
First-ever government guidance for Model Context Protocol (May 2026). mTLS, tool scoping, audit requirements.
Read Guidance →Semantic Kernel RCE
CVE-2026-25592 and CVE-2026-26030: Two critical RCE vulnerabilities in Microsoft Semantic Kernel via prompt injection.
View Details →HF Backdoor Models
50K+ downloads of Hugging Face models with hidden backdoor triggers. AI supply chain attacks on the rise.
Citiți mai multe →Resurse populare
Metodologie
Structured approach to AI pentesting — from planning to reporting.
Citiți mai multe medii de intrare →Catalog de amenințări
Catalog cuprinzător al vulnerabilităților specifice AI și al vectorilor de atac.
Vizualizați amenințările →Standarde și conformitate
Rămâneți în conformitate cu cadrele și reglementările globale de securitate AI.
NIST AI RMF
Cadru de management al riscului pentru sisteme AI de încredere.
EU AI Act
European Union AI regulation — enforcement started 2026.
ISO/IEC 23053
Standard internațional pentru ingineria sistemului ML.
Cele mai recente de pe blog
Rămâneți la curent cu cele mai recente cercetări și vulnerabilități în domeniul securității AI.
Vizitați blogul →