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

Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.
Security scanner for AI/ML model files. Detects malicious code, backdoors, and vulnerabilities before deployment

Anti-LLM obfuscation via finger counting

Alignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface

Overlay network protocol giving AI agents permanent addresses, authenticated encrypted tunnels, and a trust model over UDP. Includes NAT traversal,…

A Burp Suite extension that exposes the full Montoya API as a local REST API, with Swagger UI

macOS persistence mechanism scanner with code signature verification and timeline tracking.

Delving into the Realm of LLM Security: An Exploration of Offensive and Defensive Tools, Unveiling Their Present Capabilities.

Example AI-agent taskflows and MCP servers for auditing source code, triaging issues, and detecting vulnerabilities across web, Android, and iOS…

Playbook-based adversary simulation framework that compiles JSON-defined attack paths into position-independent shellcode payloads for validating…

A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)

Cryptographically signed, replay-verifiable evidence layer for AI agents. Governs actions in the loop, produces Ed25519-signed receipts linked into a…

CVE-Factory

WASM sandbox with capability enforcement for AI agent code. Agents can only call explicitly provided tools with defined constraints. Sandboxed…

Security training for the apps you actually ship. Open your browser and start hacking.

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

AI 驱动的 SOC 仿真平台

Project Mantis: Hacking Back the AI-Hacker; Prompt Injection as a Defense Against LLM-driven Cyberattacks