Compare skills
Pick 2–4 skills and compare what really matters: fit, risk, install effort, and community signal.
Comparison matrix
Highlights show current best; tooltip explains diff/best rules.
SAS-v2.1 diff rules / risk tag notes
Start with the matrix. Open this section when you need to understand audit grades, top threats, control gaps, and best-value highlights.
skill-seekers
openclaw/skills · Score 88
Search to add skills, or paste 2–4 comma-separated slugs.
How differences are detected
A row is marked different when selected skills have distinct values. Only-differences mode hides rows that are identical.
How best values are highlighted
Audit score, evidence confidence, trust score, and community signal prefer higher values; execution risk and install friction prefer lower values.
How to read risk tags
Risk tags come from SAS-v2.1 public-evidence signals and point to command, network, secret, context, or supply-chain items to review before install.
Selected audit signals
Self Improving Agent
Execution risk：High
Threat tags：unexpected code execution, identity privilege abuse, data exfiltration
Control gaps：missing repo, missing license, unclear tool boundary
Vercel
Execution risk：High
Threat tags：unexpected code execution, identity privilege abuse, data exfiltration
Control gaps：missing license, broad permissions, shell without guardrails
Binance Onchain Pay
Execution risk：High
Threat tags：unexpected code execution, identity privilege abuse, data exfiltration
Control gaps：missing license, broad permissions, shell without guardrails
skill-seekers
Execution risk：High
Threat tags：unexpected code execution, identity privilege abuse, data exfiltration
Control gaps：missing license, broad permissions, shell without guardrails
| Dimension | Self Improving Agent | Vercel | Binance Onchain Pay | skill-seekers |
|---|---|---|---|---|
| SAS-v2.1 pre-install audit | ||||
Audit grade | D · Limited evidence | C · Review first | C · Review first | D · Limited evidence |
Execution risk | High | High | High | High |
Threat tags | unexpected code execution, identity privilege abuse, data exfiltration | unexpected code execution, identity privilege abuse, data exfiltration | unexpected code execution, identity privilege abuse, data exfiltration | unexpected code execution, identity privilege abuse, data exfiltration |
Control gaps | missing repo, missing license, unclear tool boundary | missing license, broad permissions, shell without guardrails | missing license, broad permissions, shell without guardrails | missing license, broad permissions, shell without guardrails |
Permission summary | Permission review, Network, Secrets, Command | Permission review, Network, Secrets, Command | Permission review, Network, Secrets, Command | Permission review, Network, Secrets, Command |
Evidence confidence | 65% | 65% | 67% | 71% |
| Source & provenance | ||||
Provenance | Source needs review | openclaw/skills | openclaw/skills | openclaw/skills |
Category | Dev & Engineering | Dev & Engineering | Dev & Engineering | Dev & Engineering |
Freshness | ||||
| Risk & trust | ||||
Trust score | 72 | 85 | 85 | 88 |
Audit signals | runs shell | needs credentials, network access, runs shell | ||
| Install & compatibility | ||||
Supported tools | Codex, OpenClaw, Claude, Cursor, Universal | Cursor | Claude | Claude, Cursor, Windsurf |
Install method | instruction-only | script-backed | script-backed | script-backed |
Install friction | ||||
| Community | ||||
Stars | 5 | 0 | 0 | 0 |
2026-03-02 |
2026-03-29 |
2026-04-01 |
2026-04-04 |
needs credentials, network access, runs shell, writes files |
Permission hints | review skill metadata before install, check required credentials in skill docs | verify source provenance before install | verify source provenance before install | verify source provenance before install |
|---|
95 |
65 |
65 |
65 |
