
hol-guard
Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at…

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at…

Sandbox for AI coding agents. Runs Copilot CLI, Claude Code, OpenCode, Gemini CLI, Antigravity, Pi, goose or a plain shell inside a kernel-level…

Curated collection of LLM jailbreak prompts and bypass techniques, documenting adversarial inputs that circumvent AI model safety guardrails.

agent runtime security - zero trust, zero setup, zero latency agent sandboxing

The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation…

The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation…

Find code that runs without you asking: repo files that execute on folder open (VS Code tasks, agent hooks, MCP, devcontainers) and Python…

Curated collection of extracted system prompts from major AI chatbots including Claude, ChatGPT, Gemini, Grok, and Copilot. Updated regularly with…

Security layer for AI coding agents. Works with Claude Code, Cursor, Windsurf, Gemini CLI, OpenCode, Pi Agent and more.

A collection of awesome resources related AI security

A secure low code deception runtime framework, leveraging AI for System Virtualization.

Creates CycloneDX Bill of Materials (BOM) for your projects from source and container images. Supports many languages and package managers. Integrate…

Fully autonomous AI Agents system capable of performing complex penetration testing tasks

OWASP project for AI-assisted threat modeling, helping teams identify, analyze, and document security threats and mitigations in system designs.

Research code for measuring jailbreak attack success rates (ASR and stepwise ASR) against LLMs, with implementations of attacks such as GCG and…

a guard that blocks catastrophic agent actions

Multi-agent LLM system for autonomous penetration testing in isolated labs: planner/worker agents share asset and exploration graphs, with MITM…

AI-assisted Vulnerability Detection & Remediation platform featuring a Go endpoint agent, centralized dashboard, and vulnerability intelligence…