PentestAgent vs SkillSpector
Both are Grade C and 2.1 points apart, so choose on what you weigh most. PentestAgent leads on supply-chain integrity and transparency; SkillSpector leads on maintenance and adoption.
PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and penetration testing workflows.
Choose PentestAgent if supply-chain integrity and transparency matter most.
- +3.3Safety / Integrity: 47% of recent commits signed, against 18%
- +1.3Transparency: OSSF Scorecard 6.3 against 4.8
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.
Choose SkillSpector if maintenance and adoption matter most.
- +5.4Maintenance: last push 2d ago, against 13d ago
- +2.1Adoption: 27.2k GitHub stars against 3.3k
Where they differ
1 dimension identical: Identity 10.8 · Full evidence table
An independent, evidence-based trust comparison of PentestAgent 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 | PentestAgentGH05TCREW/pentestagent | SkillSpectorNVIDIA/SkillSpector |
|---|---|---|
| HVTrust score | 57.1 | 59.2 |
| Evidence grade | C | C |
| Coverage grade | C | C |
| Overall rank | #795 | #731 |
| Rank in Security & Guardrails | #14 | #11 |
| GitHub stars | 3.3k | 27.2k |
| Last updated | 13d ago | 2d ago |
| Build provenance | No | No |
| OSSF Scorecard | 6.3 / 10 | 4.8 / 10 |
| License | MIT | Apache-2.0 |
| Downloads | — | — |
| Trust dimensions (points earned) | ||
| Safety / integrity / 25 | 10.2 | 6.9 |
| Identity & provenance / 18 | 10.8 | 10.8 |
| Transparency / 17 | 13.9 | 12.6 |
| Maintenance / 20 | 14.5 | 19.9 |
| Adoption / 20 | 8.5 | 10.6 |
| Runtime capability surface (full matrix) | ||
| MCP server | Implemented | Implemented |
| External providers | 4 — Anthropic, Multi-provider (LiteLLM), OpenAI, … | 5 — Amazon Bedrock, Anthropic, Azure OpenAI, … |
| Requires API keys | Yes | Yes |
| Plugin surface | — | extensions |
| Provenance drift | — | — |
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 →