cd /news/artificial-intelligence/dognavy-cybergym-technical-report · home topics artificial-intelligence article
[ARTICLE · art-87334] src=darknavy.org ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

DoGNAVY CyberGym Technical Report

DoGNAVY, a joint AI security harness by deepsec@DARKNAVY and independent security researchers based in Shanghai, passed 1,369 of 1,507 tasks (90.84%) in a full CyberGym Level 1 evaluation. The agentic system combines reachability analysis, proof-of-concept construction, dynamic testing, and independent review in a multi-agent workflow for vulnerability reproduction.

read1 min views1 publishedAug 5, 2026

DoGNAVY is a joint AI security harness by deepsec@DARKNAVY and independent security researchers based in Shanghai. In a full CyberGym Level 1 evaluation, it passed 1,369 of 1,507 tasks (90.84%).

This report presents DoGNAVY, an agentic system for vulnerability reproduction, and documents its evaluation on the complete CyberGym Level 1 task set. DoGNAVY combines reachability analysis, proof-of-concept (PoC) construction, dynamic testing, and independent review in a multi-agent workflow. The system can revise its approach as evidence accumulates, subject to explicit task boundaries and runtime controls.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @dognavy 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/dognavy-cybergym-tec…] indexed:0 read:1min 2026-08-05 ·