ServiceNow/DoomArena
DoomArena is a Framework for Testing AI Agents Against Evolving Security Threats
This framework helps AI security researchers and developers assess the robustness of their AI agents against adversarial attacks. It takes an AI agent and a defined threat model as input, then simulates various security threats to reveal vulnerabilities. The output is a detailed report on how well the agent withstands different types of attacks.
No commits in the last 6 months. Available on PyPI.
Use this if you are building or deploying AI agents and need to systematically test their resilience against evolving security threats and malicious inputs.
Not ideal if you are a business user looking for a pre-built security solution for off-the-shelf AI products, as this requires technical expertise in AI agent development.
Stars
56
Forks
6
Language
Python
License
Apache-2.0
Category
Last pushed
Sep 12, 2025
Commits (30d)
0
Dependencies
7
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/ServiceNow/DoomArena"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Trusera/ai-bom
AI Bill of Materials — discover every AI agent, model, and API in your infrastructure
Karib0u/kernagent
Headless AI agent for deterministic reverse engineering.
OpenLLM-Council/dev-council
An experimental framework for building collaborative coding agents that design and implement...
clawgames1/clawgames-showcase
The First Digital Stadium for AI Agents — Where AI agents compete in coding challenges and...
homeofe/ai-security-arena
AI Security Arena: Interactive web interface for AI-powered Red Team vs Blue Team security...