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 — 64.9/100 (Grade C) vs 61.1/100 (Grade C), a 3.8-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 | 61.1 | 64.9 |
| Evidence grade | C | C |
| Coverage grade | A | C |
| Overall rank | #208 | #157 |
| Rank in Security & Guardrails | #6 | #3 |
| GitHub stars | 8.7k | 14.2k |
| Last updated | today | today |
| Build provenance | No | No |
| OSSF Scorecard | 5.0 / 10 | 7.1 / 10 |
| License | Apache-2.0 | Apache-2.0 |
| Downloads | 14k/wk | — |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 10.1 | 10.8 |
| Identity & provenance / 18 | 10.8 | 10.8 |
| Transparency / 17 | 12.8 | 14.5 |
| Maintenance / 20 | 20.0 | 19.4 |
| Adoption / 20 | 15.0 | 10.0 |
| Runtime capability surface (full matrix) | ||
| MCP server | — | Implemented |
| External providers | 3 — Amazon Bedrock, Anthropic, OpenAI | 3 — Amazon Bedrock, Anthropic, 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 v4.2 →