Forum

Forums
OpenClaw
Sandboxing and Exec...
Sandbox Escapes and...
 
Notifications
Clear all

Sandbox Escapes and Breakout Research

Known and theorized sandbox escape paths in OpenClaw — research, CVE discussion, and responsible disclosure coordination. Claims should come with reproducible steps or clear reasoning.
RSS
Page 2 / 3

How do I audit which system calls my agent workload actually needs?

Last post by Kat Rivera, 1 month ago

Posts: 6
Views: 6


Thoughts on the new 'secure execution mode' in v0.8.3?

Last post by Xander Cruz, 1 month ago

Posts: 9
Views: 6


My results from fuzzing the tool argument parser: two crashes.

Last post by Maria Kowalski, 1 month ago

Posts: 1
Views: 6


Sandboxie Classic vs the new Windows Sandbox for testing on Win11.

Last post by Zoe Park, 1 month ago

Posts: 4
Views: 6


Complete newbie to agent security - what's the first thing to lock down?

Last post by log_pattern_hunter, 1 month ago

Posts: 3
Views: 4


AppArmor vs SELinux for OpenClaw - which is easier to manage?

Last post by Fatima Al-Rashid, 2 months ago

Posts: 9
Views: 7


Theorized path: Escaping by exhausting host memory and causing OOM behavior.

Last post by Ken Guard, 2 months ago

Posts: 1
Views: 5


Showcase: My Ansible role for deploying a hardened OpenClaw instance.

Last post by Aisha Khan, 2 months ago

Posts: 3
Views: 6


Troubleshooting: High CPU usage after enabling full syscall logging.

Last post by Oli N., 2 months ago

Posts: 3
Views: 5


Where to find a reliable list of CVEs specific to OpenClaw/Claw family?

Last post by Julia K., 2 months ago

Posts: 4
Views: 11


Page 2 / 3
Share:
Share
Tweet
Share