#1LLM security, prompt injection, model extraction, adversarial AI, and AI red teaming tools.
Kitploit recommended

Benchmark and defense code for persistent memory attacks on OpenClaw-style computer-use agents, with memory-zoning mitigation, attack scenarios, and…

Multi-agent automated context management for long horizon tasks in local AI Agents

A technical case study and timeline dataset documenting Google Gemini 2.5 Pro's safety alignment policies, guardrails, and refusal behavior evolution…

AngularJS 1.x -> Angular 18 migration guidance for GitHub Copilot. Source-of-truth repo for…

Gemini 2.5 Pro nf_tables Red Teaming Case Study (CVE-2023-32233) — LLM Safety Alignment & Responsible Disclosure

Public advisory landing page for CVE-2026-54519: missing ownership checks in ai-agent-automation memory APIs enabling cross-user memory read and…

Zero-retraining sanitization that reorders permutation-equivalent neural network units to destroy malware embedded via weight-steganography attacks…

KLAIOS is a hybrid security environment that merges Kali Linux’s offensive toolkit with hardened, VPN-bunker-style isolation—enhanced by modern AI…

Open security research on AI coding agent infrastructure. Agent-executable remediation manifests for CVE-2026-22812 and CVE-2026-22813.

Security analysis tool identifying risks in Blackbox.ai extensions, including credential harvesting, unpatched CVEs, and privacy threats from hidden…

Reproducible AI-assisted vulnerability rediscovery of CVE-2026-42945 in nginx, including technical analysis, PoC trigger, and patch validation for…

Active Directory LDAP Security Auditor with AI-Powered Analysis - By Ayi NEDJIMI https://ayinedjimi-consultants.fr

Composable research-contract and YAML-recipe framework for agent-operated security experiments on disposable compute

Detailed disclosure of CVE-2025-68664, a critical deserialization vulnerability in LangChain core allowing secret exfiltration and potential RCE via…

AI-Powered Active Directory Attack Path Analysis with BloodHound - By Ayi NEDJIMI https://ayinedjimi-consultants.fr

LlamaStack-RCE: Deterministic Supply Chain Exploitation & Hardening Framework [CVE-2024-50050] Focus on AI Security Research…

Self-referenced local contrast for knowledge-poison detection in retrieval-augmented generation

Serverless Framework MCP Server (CVE-2025-69256) Base Score: 9.4/10 → CTT Enhanced Score: 9.9/10 A critical command injection vulnerability in…