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.
Suggested baseline
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
security-ownership-map
Execution risk：High
Threat tags：data exfiltration, human approval gap
Control gaps：missing license, broad permissions, network without allowlist
TwelveLabs Video Intelligence
Execution risk：High
Threat tags：unexpected code execution, identity privilege abuse, data exfiltration
Control gaps：missing license, broad permissions, shell without guardrails
openai-fm
Execution risk：High
Threat tags：unexpected code execution, data exfiltration, human approval gap
Control gaps：missing license, broad permissions, shell without guardrails
| Dimension | security-ownership-map | TwelveLabs Video Intelligence | openai-fm |
|---|---|---|---|
| SAS-v2.1 pre-install audit | |||
Threat tags | data exfiltration, human approval gap | unexpected code execution, identity privilege abuse, data exfiltration | unexpected code execution, data exfiltration, human approval gap |
Control gaps | missing license, broad permissions, network without allowlist | missing license, broad permissions, shell without guardrails | missing license, broad permissions, shell without guardrails |
Permission summary | Permission review, Network, Command | Permission review, Network, Secrets, Command | Permission review, Network, Command |
Evidence confidence | 67% | 67% | 65% |
| Source & provenance | |||
Provenance | openai/skills/tree/main/skills/.curated/security-ownership-map | openclaw/skills | openai/openai-fm |
Category | Data & Analytics | Knowledge & RAG | Automation & Workflows |
Freshness | |||
| Risk & trust | |||
Trust score | 82 | 85 | 92 |
Audit signals | writes files | needs credentials, network access, runs shell, writes files | metadata-only |
| Install & compatibility | |||
Supported tools | Claude, Codex, Cursor, Universal | OpenClaw | Universal |
Install method | registry-install | script-backed | script-backed |
Install friction | |||
| Community | |||
Stars | 7.3K | 0 | 2.8K |
Repository: openai-realtime-console
Author: openai · Source status: Clear source
React app for inspecting, building and debugging with the Realtime API
Score basis：Clear source · Risk needs review · Universal
Repository: human-eval
Author: openai · Source status: Clear source
Code for the paper "Evaluating Large Language Models Trained on Code"
Score basis：Clear source · Risk needs review · Universal
Repository: gpt-discord-bot
Author: openai · Source status: Clear source
Example Discord bot written in Python that uses the completions API to have conversations with the `text-davinci-003` model, and the moderations API to filter the messages.
Score basis：Clear source · Risk needs review · Universal
2026-02-11 |
2026-04-03 |
2026-03-04 |
Permission hints |
|---|
registry access, remote metadata pull, runtime dependencies may be required |
requires binary: python3, verify source provenance before install |
repository clone |
50 |
65 |
75 |
