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.
litellm
BerriAI/litellm · Score 92
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
oss-llmops-stack
Execution risk：High
Threat tags：prompt injection, tool poisoning, unexpected code execution
Control gaps：missing license, broad permissions, shell without guardrails
Agent Sync
Execution risk：High
Threat tags：prompt injection, tool poisoning, unexpected code execution
Control gaps：missing license, broad permissions, shell without guardrails
devopness
Execution risk：High
Threat tags：prompt injection, tool poisoning, unexpected code execution
Control gaps：missing license, broad permissions, shell without guardrails
litellm
Execution risk：High
Threat tags：unexpected code execution, data exfiltration, human approval gap
Control gaps：missing license, broad permissions, shell without guardrails
| Dimension | oss-llmops-stack | Agent Sync | devopness | litellm |
|---|---|---|---|---|
| SAS-v2.1 pre-install audit | ||||
Threat tags | prompt injection, tool poisoning, unexpected code execution | prompt injection, tool poisoning, unexpected code execution | prompt injection, tool poisoning, unexpected code execution | unexpected code execution, data exfiltration, human approval gap |
| Source & provenance | ||||
Provenance | langfuse/oss-llmops-stack | openclaw/skills | devopness/devopness | BerriAI/litellm |
Category | Automation & Workflows | Dev & Engineering | Operations & Infra | Automation & Workflows |
Freshness | 2025-02-16 | 2026-04-05 | 2026-04-08 | 2026-04-14 |
| Risk & trust | ||||
Trust score | 83 | 84 | 79 | 92 |
Audit signals | metadata-only | network access, runs shell, writes files | ||
| Install & compatibility | ||||
Supported tools | Universal | Claude, Codex, Cursor, OpenClaw, Windsurf, GitHub Copilot | Universal | Universal |
Install friction | 75 | 50 | 40 | |
| Community | ||||
Stars | 136 | 0 | 367 | 43.2K |
metadata-only |
Permission hints | repository clone | target os: macos, target os: linux, verify source provenance before install | repository clone, local runtime dependencies | repository clone |
|---|
75 |
