Python · Apache-2.0
NVIDIA/SkillSpector
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.
★ 24.4k
Stars
2.1k forks · 153 open issues
+172/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
70.5
Momentum / 100
see the breakdown below
7mo ago
Created
last push 3d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 42.8 | +172/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.99× the monthly pace |
| Freshness | 15 | 15.0 | last push 3d ago; decays to zero at 180 days |
| Scale | 15 | 12.7 | 24.4k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 70.5 | sum of the above |
Detail
| Topics | agent-securityagent-skillsagentic-aiai-securityclaude-codemcpprompt-injectionsecurity-scannersecurity-toolssecurity-workflowsupply-chain-security |
| Matched on | AI Agents (agentic-ai) Agent Skills & MCP (agent-skills, mcp) Security (security-tools) |
| Short window | +1.2k stars over 7 days = 172.1/day |
| Long window | +4.5k stars over 26 days = 174.7/day |
| Lifetime average | 106.47 stars/day over 229 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |