Agentic AI security scanner that hunts exploitable vulnerabilities like an adversary, proves them with executable PoCs, and fixes them test-first. A maintained fork of Capital One's VulnHunter, rebuilt for any agent harness.
nealbridges/VulnHunter is drawing steady momentum at +2.1 stars/day (45th percentile in the tracked cohort), for a momentum score of 29.7/100. Forks are climbing too, at +0.3/day.
Low breakout odds over the next 14 days, led by push recency (78th pctl). Confidence is moderate given the available history.
Reconstructed from 13 snapshots — the time-series GitHub’s API doesn’t expose.
Live score, refreshed every 6 hours. Links back to this page.
[](https://repoclimb.com/repo/nealbridges/VulnHunter)Transparent heuristic · logged for model training
Percentile rank within the tracked cohort. The score self-calibrates — it answers “accelerating vs. everything else,” not raw size.