invariantlabs-ai / mcp-injection-experimentsLinks
Code snippets to reproduce MCP tool poisoning attacks.
β132Updated last month
Alternatives and similar repositories for mcp-injection-experiments
Users that are interested in mcp-injection-experiments are comparing it to the libraries listed below
Sorting:
- MCPSafetyScanner - Automated MCP safety auditing and remediation using Agents. More info: https://www.arxiv.org/abs/2504.03767β68Updated last month
- π₯π Awesome MCP (Model Context Protocol) Security π₯οΈβ193Updated last week
- Top 10 for Agentic AI (AI Agent Security)β110Updated last week
- A MCP server for using Semgrep to scan code for security vulnerabilities.β175Updated this week
- The LLM Red Teaming Frameworkβ228Updated this week
- Constrain, log and scan your MCP connections for security vulnerabilities.β741Updated this week
- A plugin-based gateway that orchestrates other MCPs and allows developers to build upon it enterprise-grade agents.β183Updated last month
- β40Updated 8 months ago
- An Execution Isolation Architecture for LLM-Based Agentic Systemsβ80Updated 4 months ago
- Experimental tools to backdoor large language models by re-writing their system prompts at a raw parameter level. This allows you to poteβ¦β168Updated 2 months ago
- All things specific to LLM Red Teaming Generative AIβ25Updated 7 months ago
- https://arxiv.org/abs/2412.02776β54Updated 6 months ago
- CVE-Bench: A Benchmark for AI Agentsβ Ability to Exploit Real-World Web Application Vulnerabilitiesβ53Updated last month
- A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)β113Updated 5 months ago
- Project Mantis: Hacking Back the AI-Hacker; Prompt Injection as a Defense Against LLM-driven Cyberattacksβ68Updated last week
- MCP Server for Burpβ115Updated last month
- MCP for Security: A collection of Model Context Protocol servers for popular security tools like SQLMap, FFUF, NMAP, Masscan and more. Inβ¦β152Updated 2 weeks ago
- LLM | Security | Operations in one github repo with good links and pictures.β29Updated 5 months ago
- Guardrails for secure and robust agent developmentβ285Updated 3 weeks ago
- A collection of prompt injection mitigation techniques.β23Updated last year
- A security scanner for your LLM agentic workflowsβ550Updated last week
- The D-CIPHER and NYU CTF baseline LLM Agents built for NYU CTF Benchβ77Updated last month
- β22Updated 4 months ago
- A very simple open source implementation of Google's Project Naptimeβ150Updated 2 months ago
- All-in-one security testing toolbox that brings together popular open source tools through a single MCP interface. Connected to an AI ageβ¦β94Updated last month
- β109Updated 2 weeks ago
- Codebase of https://arxiv.org/abs/2410.14923β47Updated 7 months ago
- This is The most comprehensive prompt hacking course available, which record our progress on a prompt engineering and prompt hacking courβ¦β78Updated last month
- A Model Context Protocol (MCP) server for querying the VirusTotal API.β55Updated 3 months ago
- XBOW Validation Benchmarksβ92Updated last week