Garak vs SkillSpector
An independent, evidence-based trust comparison of Garak 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.
SkillSpector leads on trust — 62.4/100 (Grade C) vs 56.9/100 (Grade C), a 5.5-point gap. Note: SkillSpector's evidence coverage is thinner (coverage C vs A) — its score rests on fewer independent signal types. Full breakdown below.
| Signal | Garakleondz/garak | SkillSpectorNVIDIA/SkillSpector |
|---|---|---|
| HVTrust score | 56.9 | 62.4 |
| Evidence grade | C | C |
| Coverage grade | A | C |
| Overall rank | #270 | #219 |
| Rank in Security & Guardrails | #6 | #4 |
| GitHub stars | 9.3k | 18.0k |
| Last updated | 5d ago | 3d ago |
| Build provenance | No | No |
| OSSF Scorecard | 4.7 / 10 | 5.4 / 10 |
| License | Apache-2.0 | Apache-2.0 |
| Downloads | 9k/wk | — |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 9.3 | 10.1 |
| Identity & provenance / 18 | 10.8 | 10.8 |
| Transparency / 17 | 12.5 | 13.1 |
| Maintenance / 20 | 18.8 | 19.8 |
| Adoption / 20 | 14.8 | 10.2 |
| Runtime capability surface (full matrix) | ||
| MCP server | — | Implemented |
| External providers | 8 — Amazon Bedrock, Anthropic, Cohere, … | 5 — Amazon Bedrock, Anthropic, Azure OpenAI, … |
| Requires API keys | Yes | Yes |
| Plugin surface | plugins | extensions |
| Provenance drift | Warning | — |
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 →