Mitre Atlas Python Packages

genai-incidents

Single source of truth for GenAI and agentic AI security incidents, mapped to OWASP LLM Top 10, OWASP Agentic Top 10 (ASI), NIST AI RMF, and MITRE ATLAS.

ai-blackteam

Automated LLM red-teaming framework. 1,028 attack techniques, reasoning-layer attacks, and five compliance scorecards (OWASP, MITRE ATLAS, EU AI Act). Vendor-neutral, GPL-3.0.

wrg-ai-security-toolkit

Offensive & defensive AI/LLM security tools, labs, CTF writeups, and research. Zero-dependency Python toolkit.

mitre-atlas-mcp

🔌 Exposes MITRE ATLAS (adversarial AI) threat landscape over MCP — MIT

ai-act-companion

Local-first, explainable EU AI Act risk classifier with risk-assessment/DPIA/bias/AI-security generators (NIST AI RMF, OWASP LLM Top 10, MITRE ATLAS) - runs as a Claude Code plugin.

norviq

Runtime security platform for LLM agent tool calls on Kubernetes

gsh-framework

Open-source hunt playbooks and a policy-driven Sentinel reference framework for detecting runaway AI agents, unauthorized tool calls, behavioral drift, DNS exfiltration, and poisoned MCP tools. MITRE ATLAS mapped.

finagent-redrange

Reproducible, defensive red-team range for financial-services AI agents: 5 POC exploits against a mock banking agent, each proven blocked by its control and mapped to OWASP / MITRE ATLAS / NIST AI RMF.

contrastapi

MCP server with 55 security intelligence tools — CVE/KEV, MITRE ATLAS+D3FEND, Sigma detection rules, email security posture (SPF/DMARC), domain & web intel, threat intel.

mcpmap

Static attack surface analyzer for MCP servers and LLM tool definitions

agentdfir

Forensic reconstruction for AI-agent security incidents — local-first, standards-aligned, zero-dependency defensive DFIR (integrity, chain of custody, MITRE ATLAS, EU AI Act Art.12).

arascan

Zero-config static security scanner for AI agents. Detects 20 vulnerability categories mapped to MITRE ATLAS and OWASP LLM Top 10.

aitdp

AI Threat Detection Protocol — open spec, community ruleset and reference SDK for detecting prompt injection, jailbreaks, data exfiltration and tool abuse in LLM apps and AI agents.

ionsec-trace

TRACE — AI and compute forensic evidence collector by IONSEC. Python CLI and Go binary with near-identical capabilities: 27 collectors, 47 shadow-AI tool detections, 103-rule secret detection, conversation forensics, MITRE ATLAS/ATT&CK, kill chain, risk scoring, HTML/JSON/STIX reports, Velociraptor artifacts.

garak-multilingual

Turkish + multilingual prompt-injection, jailbreak & casefold-evasion probes for NVIDIA garak — test your LLM's non-English attack surface. OWASP LLM Top 10 / MITRE ATLAS mapped.

shipgrade

Grade your LLM feature before you ship. A-to-F safety and regulated-domain compliance card, offline in 60s.

infiltr

RL-based LLM red-team framework with MITRE ATLAS reporting and CI-ready outputs