Deepsec vs HOL Guard
HOL Guard leads on trust: 91.3/100 (Grade A) against 60.7/100 (Grade C), a 30.6-point gap. HOL Guard leads on supply-chain integrity and provenance, and rests on broader evidence.
Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents
Deepsec doesn't lead on any scored dimension in this pair.
Open-source antivirus and firewall for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
Choose HOL Guard if supply-chain integrity and provenance matter most.
- +12.4Safety / Integrity: OSSF Scorecard 8.8 against 4.9
- +7.2Identity / Provenance: package provenance attested, against none
- +3.3Transparency: OSSF Scorecard 8.8 against 4.9
- +3.3Maintenance: last push today, against 2d ago
Where they differ
An independent, evidence-based trust comparison of Deepsec and HOL Guard, two Security & Guardrails projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.
Full evidence
| Signal | Deepsecvercel-labs/deepsec | HOL Guardhashgraph-online/hol-guard |
|---|---|---|
| HVTrust score | 60.7 | 91.3 |
| Evidence grade | C | A |
| Coverage grade | C | B |
| Overall rank | #682 | #18 |
| Rank in Security & Guardrails | #10 | #2 |
| GitHub stars | 8.5k | 1.1k |
| Last updated | 2d ago | today |
| Build provenance | No | Yes |
| OSSF Scorecard | 4.9 / 10 | 8.8 / 10 |
| License | Apache-2.0 | Apache-2.0 |
| Downloads | — | 5k/wk |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 11.1 | 23.5 |
| Identity & provenance / 18 | 10.8 | 18.0 |
| Transparency / 17 | 12.7 | 16.0 |
| Maintenance / 20 | 16.7 | 20.0 |
| Adoption / 20 | 9.4 | 12.3 |
| Runtime capability surface (full matrix) | ||
| MCP server | — | Implemented |
| External providers | — | 3 — Anthropic, Google Gemini, Multi-provider (LiteLLM) |
| Requires API keys | No | No |
| Plugin surface | — | 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 v4.4 →