Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
NVIDIA/SkillSpector is drawing steady momentum at +244.4 stars/day (97th percentile in the tracked cohort), for a momentum score of 67.7/100. A recent release is helping fuel the run.
Reconstructed from 233 snapshots — the time-series GitHub’s API doesn’t expose.
Release count rose to 21.
Release count rose to 20.
Release count rose to 19.
Live score, refreshed every 6 hours. Links back to this page.
[](https://repoclimb.com/repo/NVIDIA/SkillSpector)Moderate breakout odds over the next 14 days, led by star velocity (97th pctl) and fork velocity (95th pctl). Confidence is high given the available history.
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.
Release count rose to 18.
~20 forks/day, 3.2× the trailing baseline.
~10 forks/day, 3.9× the trailing baseline.
Release count rose to 17.
~27 forks/day, 4.5× the trailing baseline.
Release count rose to 16.
Release count rose to 15.
~45 forks/day, 3.4× the trailing baseline.