#1LLM security, prompt injection, model extraction, adversarial AI, and AI red teaming tools.
Kitploit recommended
dshapi/ai-spmThis opensource project dedicated to implementing Enterprise level AI-SPM. By doing so organizations can proactively protect their AI systems from…
aniketkarne/aco-prompt-shieldStop prompt injection attacks before they reach your LLM — zero API costs, runs entirely locally, integrates in 2 minutes. Prompt injection is the…
weareaisle/nano-analyzerA minimal LLM-powered zero-day vulnerability scanner by AISLE.
pathakabhi24/llm-mcp-security-field-guideThe most comprehensive LLM + MCP security guide i.e. OWASP aligned, real CVEs, actionable checklists
find-lab/agentwardFull-stack security OS for AI agents with five-layer defense-in-depth architecture covering foundation scan, input sanitization, cognition…
cgrtml/reasongateExplainable security gate for LLM apps — blocks prompt injection with an auditable reason for every decision.
msaad00/agent-bomOpen security scanner and self-hosted control plane for AI, MCP, and cloud. One evidence model — run scans in your environment, centralize findings,…
ageofalgorithms/mahoraga-webapp-defenderAI-powered reactive website defense system that detects attacks, analyzes them, and autonomously patches source code in real-time using LLM agents.
infisical/agent-vaultA HTTP credential proxy and vault for AI agents like Claude Code, OpenClaw, Hermes, custom agents + harnesses, and more.
kpolley/redaiAI-driven vulnerability discovery and live validation
francescostabile/numasecAI security agent that runs in your terminal, orchestrating local tools, runbooks, and agents for authorized AppSec, pentest, OSINT, and CTF…
gautamvarmadatla/mcpsafetywardenProxy server that wraps MCP servers with behavioral profiling, security scanning, risk gating, and safe execution. Detects prompt injection,…
nanocoai/nanoclawA lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging…
capsulerun/capsuleSecure runtime to sandbox AI agent tasks. Run untrusted code in isolated WebAssembly environments.
pilot-protocol/pilotprotocolOverlay network protocol giving AI agents permanent addresses, authenticated encrypted tunnels, and a trust model over UDP. Includes NAT traversal,…
seqra/opentaintFormal inter-procedural taint analysis engine for application security. Tracks untrusted data across function boundaries, persistence layers, and…
calusdotai/anticipatorAnticipator is an open-source threat detection platform for multi-agent AI systems.
