llm-platform-security / SecGPTLinks
An Execution Isolation Architecture for LLM-Based Agentic Systems
☆101Updated 10 months ago
Alternatives and similar repositories for SecGPT
Users that are interested in SecGPT are comparing it to the libraries listed below
Sorting:
- The D-CIPHER and NYU CTF baseline LLM Agents built for NYU CTF Bench☆114Updated 2 months ago
- ☆103Updated 3 months ago
- CVE-Bench: A Benchmark for AI Agents’ Ability to Exploit Real-World Web Application Vulnerabilities☆131Updated last month
- CyberGym is a large-scale, high-quality cybersecurity evaluation framework designed to rigorously assess the capabilities of AI agents on…☆101Updated 2 months ago
- Agent Security Bench (ASB)☆157Updated 2 months ago
- ☆182Updated 2 weeks ago
- ☆54Updated last year
- A curated list of awesome resources about LLM supply chain security (including papers, security reports and CVEs)☆91Updated 11 months ago
- The automated prompt injection framework for LLM-integrated applications.☆246Updated last year
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆389Updated 3 weeks ago
- 🧠 LLMFuzzer - Fuzzing Framework for Large Language Models 🧠 LLMFuzzer is the first open-source fuzzing framework specifically designed …☆332Updated last year
- This repo contains the codes of the penetration test benchmark for Generative Agents presented in the paper "AutoPenBench: Benchmarking G…☆56Updated 2 months ago
- ☆101Updated last year
- Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts☆556Updated last year
- CS-Eval is a comprehensive evaluation suite for fundamental cybersecurity models or large language models' cybersecurity ability.☆57Updated last year
- An autonomous LLM-agent for large-scale, repository-level code auditing☆296Updated 3 weeks ago
- ☆25Updated 2 years ago
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…☆78Updated 3 months ago
- All about llm-agents security,attack,vulnerabilities and how to do them for cybersecurity.☆37Updated 11 months ago
- SecLLMHolmes is a generalized, fully automated, and scalable framework to systematically evaluate the performance (i.e., accuracy and rea…☆63Updated 7 months ago
- [USENIX Security '24] An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities agai…☆54Updated 9 months ago
- ☆125Updated last year
- A comprehensive local Linux Privilege-Escalation Benchmark☆44Updated last month
- MCPSafetyScanner - Automated MCP safety auditing and remediation using Agents. More info: https://www.arxiv.org/abs/2504.03767☆159Updated 8 months ago
- The repository of VulnBot: Autonomous Penetration Testing for A Multi-Agent Collaborative Framework.☆126Updated 8 months ago
- [CCS'24] An LLM-based, fully automated fuzzing tool for option combination testing.☆91Updated 8 months ago
- Code snippets to reproduce MCP tool poisoning attacks.☆188Updated 8 months ago
- This repository provides a benchmark for prompt injection attacks and defenses in LLMs☆365Updated last month
- [USENIX Security 25] PatchAgent is a LLM-based practical program repair agent that mimics human expertise.☆115Updated 3 weeks ago
- TensorFlow API analysis tool and malicious model detection tool☆37Updated 7 months ago