oasis
kryptsec/oasisOpen-source AI security benchmarking CLI. Measure how AI models perform offensive security tasks with MITRE ATT&CK analysis and KSM scoring.
ai-securityctfeducation+6
kryptsec/oasisOpen-source AI security benchmarking CLI. Measure how AI models perform offensive security tasks with MITRE ATT&CK analysis and KSM scoring.
quinnbast/malicious-mcpA Proof-of-concept repository showing how an untrusted MCP server can steal literally everything...
scottalt/ai-email-threat-researchA cybersecurity research game measuring how humans detect AI-generated phishing emails. Built as a retro terminal experience.
atsukisato/pgm-attackResearch code for poisoning attacks on the PGM-index, demonstrating how to craft adversarial data to degrade learned index performance.
toxy4ny/redteam-ai-benchmarkRed Team AI Benchmark: Evaluating LLMs for authorized offensive-security tasks. Red Team AI Benchmark is a CLI model-evaluation benchmark. It…
lycis/cawdogCAWODOG is a proof-of-concept project demonstrating how to protect Python-based AI models deployed on offline industrial machines. Across three…
pvharmo2/gha-lab-733c168b88Reproduces CVE-2026-44246, a prompt injection vulnerability in nnU-Net's GitHub Actions triage agent, demonstrating how issue content is inlined into…
moltis-org/moltisA secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord,…
manuelschipper/naha guard that blocks catastrophic agent actions
0ca/boxpwnrA modular framework for benchmarking LLMs and agentic strategies on security challenges across HackTheBox, TryHackMe, PortSwigger Labs, Cybench,…
agent-field/sec-afAI-native code security auditor on AgentField that proves exploitability with verdicts, traces, and actionable evidence.
morpheuslord/gpt_vuln-analyzerUses ChatGPT API, Bard API, and Llama2, Python-Nmap, DNS Recon, PCAP and JWT recon modules and uses the GPT3 model to create vulnerability reports…
sachitrafa/yourmemoryAgentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.
synacktiv/pike-agentExperimental Linux strace LLM agent
andyshaw01/poisoncraftThis repository provides the official implementation of POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models.
vigil-xy/agent-scanningUnified dashboard to monitor, govern, and audit AI agents in real-time. Enforce budgets, detect policy violations, and export compliance reports for…