invariantlabs-ai / mcp-injection-experiments
Code snippets to reproduce MCP tool poisoning attacks.
β113Updated 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:
- π₯π Awesome MCP (Model Context Protocol) Security π₯οΈβ159Updated this week
- MCPSafetyScanner - Automated MCP safety auditing and remediation using Agents. More info: https://www.arxiv.org/abs/2504.03767β51Updated last month
- A MCP server for using Semgrep to scan code for security vulnerabilities.β148Updated 2 weeks ago
- An Execution Isolation Architecture for LLM-Based Agentic Systemsβ79Updated 3 months ago
- CVE-Bench: A Benchmark for AI Agentsβ Ability to Exploit Real-World Web Application Vulnerabilitiesβ43Updated 2 weeks ago
- MCP for Security: A collection of Model Context Protocol servers for popular security tools like SQLMap, FFUF, NMAP, Masscan and more. Inβ¦β102Updated this week
- All-in-one security testing toolbox that brings together popular open source tools through a single MCP interface. Connected to an AI ageβ¦β78Updated 3 weeks ago
- β22Updated 3 months ago
- LLM | Security | Operations in one github repo with good links and pictures.β29Updated 4 months ago
- π€π‘οΈπππ Tiny package designed to support red teams and penetration testers in exploiting large language model AI solutions.β23Updated 11 months ago
- This is The most comprehensive prompt hacking course available, which record our progress on a prompt engineering and prompt hacking courβ¦β69Updated last month
- The D-CIPHER and NYU CTF baseline LLM Agents built for NYU CTF Benchβ71Updated last month
- MCP Server for Burpβ76Updated 2 weeks ago
- A security scanning tool for MCP serversβ624Updated this week
- A Model Context Protocol (MCP) server for querying the CVE-Search APIβ17Updated last week
- YuraScannerβ42Updated 3 months ago
- Top 10 for Agentic AI (AI Agent Security)β99Updated 2 months ago
- A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)β109Updated 4 months ago
- https://arxiv.org/abs/2412.02776β53Updated 5 months ago
- β37Updated 7 months ago
- β100Updated 2 months ago
- β96Updated last week
- β14Updated 4 months ago
- LLM Agent and Evaluation Framework for Autonomous Penetration Testingβ102Updated 5 months ago
- A plugin-based gateway that orchestrates other MCPs and allows developers to build upon it enterprise-grade agents.β157Updated 3 weeks ago
- Experimental tools to backdoor large language models by re-writing their system prompts at a raw parameter level. This allows you to poteβ¦β165Updated last month
- XBOW Validation Benchmarksβ88Updated 8 months ago
- NOT for educational purposes: An MCP server for professional penetration testers including nmap, go/dirbuster, nikto, JtR, wordlist buildβ¦β33Updated last week
- A very simple open source implementation of Google's Project Naptimeβ142Updated last month
- A Model Context Protocol (MCP) server for querying the VirusTotal API.β51Updated 2 months ago