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

cMCP: Confidential MCP Gateway. Hardware-attested policy enforcement for MCP tool calls.
Security proxy for AI agents. Scans every message for prompt injection, PII, and secrets. Defense-in-depth: Go proxy + iptables firewall + eBPF…

AI runtime inventory: discover shadow AI, trace LLM calls

Evades LLM text watermarks by injecting Unicode variation selectors; includes the SynthID generator, mean-g detector, normalization defenses, and…

LLM agent solving traces, leaderboards, and benchmark results across security CTF and hacking platforms

Open-weight LLMs and training/evaluation code for defending against prompt injection attacks, with benchmarks for agentic tool-calling and…

NOVA - Claude Code Protection System against prompt injection attacks

An autonomous red-teaming engine for LLMs. RedThread manages the full security lifecycle: generating adversarial attacks, executing precision…

Self-hosted threat intelligence platform — feed aggregation, AI triage, MITRE ATT&CK coverage, and Sentinel-integrated detection engineering. Runs…

Claude Code and Codex skill for finding potentially vulnerable Brotli copies and guiding updates for CVE-2026-111497.

Automated steganography detection tool that scans websites, web servers, and local directories using AI-driven object/text recognition and deep file…

Runtime protection for AI agents

Skillscript — a small declarative language for authoring agent workflows. Runtime, compiler, and CLI.

Powerful protection for AI agents - Open-source security and cost tracking for AI applications

AI supply-chain BOM: every agent, MCP server and AI package, and what each one can reach. Open-source scanner and self-hosted control plane for code,…

Moxy is an open-source DAST tool designed for modern web application security testing. It provides an easy-to-use interface with agentic capabilities…

Keep private data, internal infrastructure and secrets out of cloud coding agents without breaking your workflow.

Android deeplink misconfiguration detector and exploitation tool