Registry › Compare › open-kritt vs SkillSpector

open-kritt vs SkillSpector

SkillSpector leads on trust: 63.3/100 (Grade C) against 57.7/100 (Grade C), a 5.6-point gap. SkillSpector leads on supply-chain integrity and adoption.

C open-kritt 57.7

Open-source, self-hosted AI vulnerability research tool that orchestrates agents to find and validate security issues in code.

Kritt-ai/open-kritt · #704 overall · #8 Security & Guardrails · coverage C (2/5)

open-kritt doesn't lead on any scored dimension in this pair.

C SkillSpector 63.3

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.

NVIDIA/SkillSpector · #532 overall · #7 Security & Guardrails · coverage C (2/5)

Choose SkillSpector if supply-chain integrity and adoption matter most.

+2.5Safety / Integrity: 88% of recent commits signed, against 51%
+2.2Adoption: 18.5k GitHub stars against 2.2k
+2.1Maintenance

Where they differ

8.5

Safety / IntegritySkillSpector +2.5

11.0

12.6

TransparencySkillSpector +0.4

13.0

17.8

MaintenanceSkillSpector +2.1

19.9

8.0

AdoptionSkillSpector +2.2

10.2

+0.0

Runtime calibrationopen-kritt +1.6

-1.6

1 dimension identical: Identity 10.8 · Full evidence table

An independent, evidence-based trust comparison of open-kritt 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.

Full evidence

Signal	open-krittKritt-ai/open-kritt	SkillSpectorNVIDIA/SkillSpector
HVTrust score	57.7	63.3
Evidence grade	C	C
Coverage grade	C	C
Overall rank	#704	#532
Rank in Security & Guardrails	#8	#7
GitHub stars	2.2k	18.5k
Last updated	today	2d ago
Build provenance	No	No
OSSF Scorecard	4.8 / 10	5.3 / 10
License	AGPL-3.0	Apache-2.0
Downloads	—	—
Trust dimensions (points earned)
Safety / integrity / 25	8.5	11.0
Identity & provenance / 18	10.8	10.8
Transparency / 17	12.6	13.0
Maintenance / 20	17.8	19.9
Adoption / 20	8.0	10.2
Runtime capability surface (full matrix)
MCP server	—	Implemented
External providers	—	5 — Amazon Bedrock, Anthropic, Azure OpenAI, …
Requires API keys	No	Yes
Plugin surface	—	extensions
Provenance drift	—	—

Open in the live compare tool → open-kritt profile SkillSpector profile More Security & Guardrails →

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 →