Search

Open-source offensive security tools, plus a vendor-agnostic AI agent that runs authorized pentest engagements using only tools from this list.

Agentic Security Fleet Ops — an LLM-agent security department with a Security Orchestrator, built on pydantic-ai with a GitHub Copilot SDK provider.

76 AI-agent security skills for Kali Linux tools — pentest, red team, forensics, OSINT, and more. Machine-readable skill definitions by Red Hound InfoSec.

AI-powered cybersecurity agent for Kali Linux that autonomously orchestrates security tools, analyzes output and maps findings to MITRE ATT&CK using Claude Agent SDK.

An autonomous reflective Go agent for full-cycle security auditing, WAF evasion, OOB LDAP verification, self-remediation (auto-patching), and compliance reporting for CVE-2021-44228 (Log4Shell).

MassAudit Pro: Next-Gen Agentic Security Auditor. Combines CodeQL's precision with LLM (DeepSeek) reasoning. Features an automated "Context-Retrieval Loop" that fetches missing function definitions to eliminate false positives. The future of SAST.

Scan TypeScript AI agent code for unguarded tool calls — pip wrapper for diplomat-agent-ts

SecureVector SDK for LangGraph — brings the local threat monitor's three controls (tool-call permissions, secret/data-leak detection, threat detection) to every LangGraph tool call, with tamper-evident audit logging.

IAM for AI agents — permission and access control framework

Official Python SDK for ABS Core — AI Agent Governance Infrastructure

Project AIR: forensic reconstruction and incident response for AI agents. Turn agent traces into signed forensic records with BLAKE3 + Ed25519.

Library-first authentication and authorization SDK for AI agents

Defense-in-depth proxy sandbox for AI agents

Track untrusted tool output before it enters prompts or actions. Python port of @mukundakatta/tool-result-taint.

Small local jailbreak and prompt-injection fixture set for tests. Python port of @mukundakatta/jailbreak-corpus-mini.

A lightweight Node.js wrapper for routing HTTP(S) traffic through Tor, including optional ControlPort circuit rotation.

Action Policy Engine for AI agents: policy-as-code for tool-calls — evaluate, enforce (block/warn/approve), and trace agent actions, with the same policy asserted in CI. Plus local guardrails and an offline judge. Pure-Python, zero dependencies.

CncertAgent local WSS log cache, offline analysis, submission, and API adapter toolkit.

Enterprise Security Monitoring SDK for AI Agents - Secure any AI agent in just 3 lines of code with real-time threat detection, behavioral analysis, and separate logging and threat reporting for comprehensive security monitoring

Codex skill for inspecting and triaging GitHub security alerts.