llm-security

Open repos and models their makers tagged llm-security, most starred first. The same for everyone.

Developer toolsRepo

iFixAi

Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds.

  • 47k
  • Python
  • Apache-2.0
  • 1 d ago
ifixai-aiTake it
AI agentsRepo

AI-Infra-Guard

A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

  • 7.6k
  • Python
  • Apache-2.0
  • 16 h ago
TencentTake it
AI agentsRepo

bla

🛡️ BLA (bla-agents / Blind LLM Agents) — Open-source Blue Defense MCP server & CLI protecting JS/TS, Electron ASAR, WASM, Python, Native Binaries, SQLite, GGUF/Safetensors & Android DEX against AI reverse-engineering agents (REA).

  • 6.2k
  • TypeScript
  • MIT
  • 1 d ago
qybaiheTake it
AI on my own machineRepo

Dark-Moon

Open-source autonomous AI penetration testing. 50 specialist agents across web, API, cloud, Active Directory, Kubernetes, CI/CD and AI/LLM (OWASP LLM Top 10). Runs on a local LLM behind a Privacy Gateway. Integrates with GitHub, GitLab, Jenkins, VS Code, JetBrains, n8n, Grafana & Splunk.

  • 1.3k
  • Python
  • AGPL-3.0
  • 7 h ago
ASCIT31Take it
GitHubRepo

Cybermes

Autonomous Offensive Security, Bug Bounty & Red Teaming Agent Framework powered by Hermes Agent, specialized reasoning skills, and multi-model LLM orchestration.

  • 1k
  • Python
  • Apache-2.0
  • 3 d ago
ZyrexnnTake it
AI agentsRepo

pipelock

Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.

  • 1k
  • Go
  • Apache-2.0
  • 16 h ago
pipelab-orgTake it
AI agentsRepo

api-relay-audit

Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks. Website: https://apirelayaudit.com

  • 923
  • Python
  • AGPL-3.0
  • 1 d ago
toby-bridgesTake it
AI agentsRepo

ship-safe

The independent security agent for AI-written software. Finds issues, investigates whether they are real, and shows you the evidence. Deterministic core, no API key needed, JSON and SARIF output.

  • 872
  • JavaScript
  • MIT
  • 5 wk ago
AI agentsRepo

coi

Give the agent a machine. Just not yours. Each AI coding agent gets its own isolated machine with root, Docker, and systemd - active defense detects and stops threats automatically.

  • 788
  • Go
  • MIT
  • 12 h ago
coipondTake it
AI agentsRepo

prismor

Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)

  • 587
  • Python
  • Apache-2.0
  • 1 d ago
PrismorSecTake it
Search GitHub and Hugging Face for llm-security

Get , open it once and sign in. Then come back here and press the button again.