HOL Guard vs SkillSpector
An independent, evidence-based trust comparison of HOL Guard and SkillSpector, two Security & Guardrails projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
HOL Guard leads on trust — 88.5/100 (Grade A) vs 63.0/100 (Grade C), a 25.5-point gap. Full breakdown below.
| Signal | HOL Guardhashgraph-online/hol-guard | SkillSpectorNVIDIA/SkillSpector |
|---|---|---|
| HVTrust score | 88.5 | 63.0 |
| Evidence grade | A | C |
| Coverage grade | B | C |
| Overall rank | #20 | #279 |
| Rank in Security & Guardrails | #1 | #8 |
| GitHub stars | 437 | 14.7k |
| Last updated | 1d ago | 1d ago |
| Build provenance | Yes | No |
| OSSF Scorecard | 7.6 / 10 | 6.3 / 10 |
| License | Apache-2.0 | Apache-2.0 |
| Downloads | 30k/wk | — |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 21.7 | 9.8 |
| Identity & provenance / 18 | 18.0 | 10.8 |
| Transparency / 17 | 15.0 | 13.9 |
| Maintenance / 20 | 19.9 | 19.1 |
| Adoption / 20 | 12.3 | 10.0 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Implemented |
| External providers | 3 — Anthropic, Google Gemini, Multi-provider (LiteLLM) | 3 — Amazon Bedrock, Anthropic, OpenAI |
| Requires API keys | Yes | Yes |
| Plugin surface | plugins | extensions |
| Provenance drift | Match | — |
How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption, scaled by an evidence-confidence factor. Grade bands: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Signals refresh daily. Full methodology v4.3 →