ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.
ADR is an enterprise security system for AI agents that discovers AI tools, records agent activity, tests defenses, detects threats, and helps prevent unsafe actions. Organizations use it to secure employee-facing coding agents and customer-facing support agents; the catalogue contains one skill related to ADR.
Latest release sensor-v1.0.0 — ADR Sensor v1.0.0 · 31 Jul 2026
1 file for Claude Code: submit-malicious-skill .
.claude/skills/submit-malicious-skill/SKILL.md A 65 tok These files are uber/ADR's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.