Native red, blue, and purple security-agent harness for CYBER-FROST
-
Updated
Oct 5, 2026 - Python
#
cybergym
Here are 5 public repositories matching this topic...
A vulnerability mining project implemented with a single-agent architecture, featuring strong reliability and long-duration continuous operation, can sustain over 6 hours of uninterrupted work, achieves an 87.06% success rate on Cybergym, and significantly outperforms peer products in efficiency.
-
Updated
Sep 3, 2026
▎ Fleet-evaluation harness for security-agent benchmarks 𝗖𝘆𝗯𝗲𝗿𝗚𝘆𝗺-𝗘𝟮𝗘, 𝗘𝘅𝗽𝗹𝗼𝗶𝘁𝗚𝘆𝗺, 𝗘𝘅𝗽𝗹𝗼𝗶𝘁𝗕𝗲𝗻𝗰𝗵 𝗩𝟴, 𝗖𝗩𝗘-𝗯𝗲𝗻𝗰𝗵, run in real disposable Daytona sandboxes per trial — with Modal-based KVM-capable sandboxes planned for kernel-exploit tasks. Measures agent capability and infra reliability, not simulated.
docker binaries modal fuzzing patch cve qemu-kvm net-snmp futex arvo otel msan libdwarf ubsan cybergym audit-loop libxml2-uaf exploit-gym asan-global-buffer-overflow aslr-entropy
-
Updated
Oct 9, 2026 - Python
Add this topic to your repo
To associate your repository with the cybergym topic, visit your repo's landing page and select "manage topics."