by uber
ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.
# Add to your Claude Code skills
git clone https://github.com/uber/ADRLast scanned: 8/4/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-08-04T06:27:23.880Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}ADR is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by uber. ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber. It has 1,446 GitHub stars.
Yes. ADR passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/uber/ADR" and add it to your Claude Code skills directory (see the Installation section above).
ADR is primarily written in Python. It is open-source under uber on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh ADR against similar tools.
No comments yet. Be the first to share your thoughts!
ADR (Agentic AI Detection and Response) is an enterprise security system for AI agents. It helps organizations secure employee-facing agents such as Cursor, Claude Code, and Codex, as well as customer-facing agents such as AI support agents.
ADR is deployed in production at Uber, and the accompanying paper was accepted to MLSys 2026: Paper PDF · Slides PDF
ADR secures enterprise AI agents through five complementary capabilities: discovering unsanctioned AI tools, observing agent activity, evaluating defenses, detecting threats, and preventing unsafe actions.
This repository contains the open-source ADR Sensor, ADR-Bench, and ADR Detector described in the paper. The offline ADR Explorer engine, which hardens ADR Detection through pre-deployment red teaming, is not included here.
| Path | ADR component | Description |
|---|---|---|
| Sensor/ | ADR Observability | Collect and normalize agent telemetry from Claude Code, Cursor, Codex, opencode, Claude Desktop, and others |
| Detection/ | ADR Benchmark + Detection | Dual-agent detector, 133 MCP servers, 303 benchmark tasks, baselines, figure scripts |
| docs/REPRODUCIBILITY.md | Evaluation | Step-by-step workflow to reproduce benchmark detection and paper figures |
git clone https://github.com/uber/ADR
cd ADR/Detection
uv sync
export ANTHROPIC_API_KEY="..." OPENAI_API_KEY="..."
Default detector is adr (ADR dual-agent). For keyless smoke tests, use --detector llamafirewall (see Detection/README.md).
See docs/REPRODUCIBILITY.md for the full evaluation workflow (inflate packed benchmark → run detectors → plot figures).
Component documentation:
@inproceedings{li2026adr,
title={ADR: An Agentic Detection System for Enterprise Agentic AI Security},
author={Li, Chenning and Hu, Pan and Xu, Justin and Ozbas, Baris and Liu, Olivia and Van, Caroline and Li, Manxue and Zhou, Wei and Alizadeh, Mohammad and Zhang, Pengyu and Sriramadhesikan, KK and Zhang, Ming},
booktitle={Proceedings of the Ninth Conference on Machine Learning and Systems},
year={2026}
}
Or use CITATION.cff.
Apache License 2.0. See LICENSE. Detection/benchmark/agentdojo/ is vendored third-party code under its own LICENSE (MIT).
Detection/ includes synthetic benchmark fixtures (fake credentials, emulated environments, prompt-injection scenarios) for defensive security research only. Details: docs/OPEN_SOURCE_REVIEW.md.