Security

An open-source AI agent for automated, autonomous penetration testing from the terminal, using a developer's own Claude, GPT or other LLM subscription across 13+ specialized agents and OWASP-based test cases.

• Security

An open-source vulnerability scanner for LLMs and agent workflows that probes for jailbreaks, fuzzes inputs across text, image and audio, and can run as a CI check to catch regressions in an AI system's safety guardrails.

• Security

Trail of Bits' opinionated collection of Claude Code defaults, documentation and workflows for security audits, development and research, covering sandboxing, permissions, hooks, skills and MCP server configuration.

• Agent skills
• Security

An HTTP credential proxy and vault that sits between AI agents and the APIs they call, so agents route requests through it instead of holding API keys directly, reducing the risk of credentials leaking through prompt injection.

• Security

A collection of 50 specialized Claude Code subagents that turn Claude into an offensive security research assistant for authorized penetration testing, covering reconnaissance, web, cloud, mobile, exploit development and reporting.

• Security

An open-source, self-hostable AI security operations center that ingests security telemetry, correlates alerts into incidents, investigates them with an auditable AI agent, and proposes a response for a human to approve, running with no API keys required.

• Security

A best-effort security scanner for AI Agent Skills that looks for prompt injection, data exfiltration and malicious code patterns using pattern matching, AST and dataflow analysis, an optional LLM-as-judge step, and a rules layer, with CI and pre-commit integration.

• Security

An open-source, self-hosted swarm of AI agents that runs autonomous penetration tests against APIs and web applications, chaining and exploiting vulnerabilities such as BOLA/IDOR, JWT forgery and SSRF rather than only scanning for them, for use in authorized testing.

• Security

A library of Claude skill files that turn Claude into an external reconnaissance operator for authorized red-team and bug-bounty engagements.

• Agent skills
• Security

Visa's open-source harness for using large language models to autonomously discover, triage, and optionally remediate software vulnerabilities.

• Security

A JADX decompiler plugin paired with an MCP server that lets an LLM analyze decompiled Android APKs live for reverse engineering and vulnerability discovery.

• MCP servers
• Security

A curated library of offensive-security skill files that gives Claude expert methodology for authorized red-team engagements, from web exploitation to wireless and cloud attack paths.

• Agent skills
• Security

A general-purpose AI search engine for problems with a known starting point and goal but an unknown path between them, first validated on autonomous penetration testing.

• Security

A security scanner that discovers every AI agent component installed on a machine, agent harnesses, MCP servers and skills, and scans them for prompt injection and other risks.

• Security

An AI agent framework for black-box penetration testing, supporting bug bounty, red-team and pentesting workflows from a terminal interface, with tools such as nmap, Metasploit and sqlmap.

• Security

An open-source, enterprise-grade MCP and agent-to-agent gateway that gives AI copilots and autonomous agents secure, governed access to internal tools, with identity management and observability.

• MCP servers
• Security

An open-source platform that gives every employee their own sandboxed AI agent, provisioned from the company identity provider and governed by one team-wide policy.

• Agent frameworks
• Security

An AI penetration-testing agent that turns a natural-language request into an automated recon, vulnerability discovery, exploitation and report-generation workflow, for authorized testing and CTF use.

• Security

An IDA Pro plugin that queries large language models to explain what a decompiled function does and to automatically rename its variables.

• Debugging
• Security

A Rust implementation of the age file encryption format, providing a simple command-line tool and library with small explicit keys and no configuration options.

• CLI tools
• Security

A Model Context Protocol server that exposes Ghidra's reverse-engineering capabilities as tools for AI agents, covering disassembly annotation, structure creation, script execution and cross-binary documentation transfer.

• MCP servers
• Security

A red-teaming and offensive-security knowledge base with cheat sheets, tools, and tips for reconnaissance, vulnerability research, exploitation, and both offensive and defensive operations.

• Security
• Curated lists

A Claude Code skill bundle for authorized bug-bounty and red-team work, with skills, slash commands and curated attack patterns drawn from disclosed vulnerability reports, plus enterprise platform attack matrices.

• Agent skills
• Security

Observability and policy enforcement for AI agent harnesses, hooking coding CLIs and chat gateways to capture every run and block dangerous tool calls before they execute.

• AI evals
• Security