Phying News
P非影 中文
Curated security research, vulnerabilities, advisories and tools for practitioners.

Rabbit r1: Innovative Device, Security Concerns

josephthacker.com | blog | #ai-security | #credential-security | #authentication | #ai-agents | #oauth | #ai-hardware | #rabbit-r1 | #vnc | #ai-devices

Summary

Joseph Thacker cautions that Rabbit's r1 AI device links user accounts via VNC logins instead of OAuth, risking credential harvesting by staff, keyloggers, or attackers gaining cross-user access.
Published
Collected

original ↗

Related coverage

  1. And another one. GitHub ships break-glass credential revocation (aikido.dev)
  2. Propagating User Identity From AI Agents to Your Tools: Amazon Bedrock AgentCore Gateway and JFrog Artifactory (jfrog.com)
  3. OAuth 2.0 Client Credentials Misuse in Public Apps (blog.sentry.security)
  4. StrikeAgent AtkBrain-Flash: Autonomous AI Penetration Testing & Red Teaming Platform (github.com)
  5. Flounder: Autonomous AI White-Hat Security Auditor with Execution-Grounded Verification (github.com)
  6. Using Genius AI Models for Important Things: Cheating at NetHack (josephthacker.com)

back