Alternatives and similar repositories for llm-security-startups

Users that are interested in llm-security-startups are comparing it to the libraries listed below

• invariantlabs-ai / invariant-gateway
  LLM proxy to observe and debug what your AI agents are doing.
  ☆64Updated 3 months ago
• cisco-ai-defense / a2a-scanner
  Scan A2A agents for potential threats and security issues
  ☆113Updated 3 weeks ago
• invariantlabs-ai / mcp-injection-experiments
  Code snippets to reproduce MCP tool poisoning attacks.
  ☆192Updated 10 months ago
• precize / Agentic-AI-Top10-Vulnerability
  Top 10 for Agentic AI (AI Agent Security) serves as the core for OWASP and CSA Red teaming work
  ☆167Updated 4 months ago
• leondz / lm_risk_cards
  Risks and targets for assessing LLMs & LLM vulnerabilities
  ☆33Updated last year
• hupe1980 / aisploit
  🤖🛡️🔍🔒🔑 Tiny package designed to support red teams and penetration testers in exploiting large language model AI solutions.
  ☆28Updated last year
• llm-platform-security / SecGPT
  An Execution Isolation Architecture for LLM-Based Agentic Systems
  ☆103Updated last year
• lasso-security / mcp-gateway
  A plugin-based gateway that orchestrates other MCPs and allows developers to build upon it enterprise-grade agents.
  ☆342Updated 2 weeks ago
• trailofbits / awesome-ml-security
  ☆156Updated 5 months ago
• lakeraai / pint-benchmark
  A benchmark for prompt injection detection systems.
  ☆158Updated last month
• andyzorigin / cybench
  ☆190Updated last month
• xvnpw / fabric-agent-action
  🤖 A GitHub action that leverages fabric patterns through an agent-based approach
  ☆34Updated last year
• Adversis / mcp-snitch
  MCP Snitch is a macOS application that intercepts and monitors MCP server communications, providing security analysis, access control, an…
  ☆93Updated 3 months ago
• Valhall-ai / prompt-injection-mitigations
  A collection of prompt injection mitigation techniques.
  ☆27Updated 2 years ago
• google-research / camel-prompt-injection
  Code for the paper "Defeating Prompt Injections by Design"
  ☆246Updated 7 months ago
• PromptDefender / PromptDefender
  A prompt defence is a multi-layer defence that can be used to protect your applications against prompt injection attacks.
  ☆21Updated last month
• sunblaze-ucb / cybergym
  CyberGym is a large-scale, high-quality cybersecurity evaluation framework designed to rigorously assess the capabilities of AI agents on…
  ☆108Updated 3 weeks ago
• OWASP / www-project-machine-learning-security-top-10
  OWASP Machine Learning Security Top 10 Project
  ☆95Updated last month
• zmre / awesome-security-for-ai
  Awesome products for securing AI systems includes open source and commercial options and an infographic licensed CC-BY-SA-4.0.
  ☆84Updated last year
• trailofbits / mcp-context-protector
  MCP security wrapper
  ☆208Updated 2 months ago
• johnhalloran321 / mcpSafetyScanner
  MCPSafetyScanner - Automated MCP safety auditing and remediation using Agents. More info: https://www.arxiv.org/abs/2504.03767
  ☆163Updated 10 months ago
• protectai / nbdefense
  Secure Jupyter Notebooks and Experimentation Environment
  ☆84Updated last year
• ZenGuard-AI / fast-llm-security-guardrails
  The fastest Trust Layer for AI Agents
  ☆152Updated last week
• wearetyomsmnv / AI-LLM-ML_security_study_map
  Do you want to learn AI Security but don't know where to start ? Take a look at this map.
  ☆29Updated last year
• mitre-atlas / atlas-data
  ATLAS tactics, techniques, and case studies data
  ☆100Updated this week
• yo-yo-yo-jbo / whisper_leak
  ☆64Updated 3 months ago
• trailofbits / pajaMAS
  Multi-agent system (MAS) hijacking demos
  ☆40Updated this week
• TalEliyahu / Awesome-AI-Security
  Curated resources, research, and tools for securing AI systems
  ☆422Updated 2 weeks ago
• meta-fun / awesome-software-supply-chain-security
  Sharing software supply chain security open source projects
  ☆53Updated 3 years ago
• wearetyomsmnv / Awesome-LLM-agent-Security
  All about llm-agents security,attack,vulnerabilities and how to do them for cybersecurity.
  ☆40Updated last month