CSKILLBOX.COM
Index live 839 skills 112 authors 10 categories Sourced from SKILL.md

Methodology

Skill security grades

Every skill in the index gets a grade from a static scan of its public SKILL.md. 801 of 839 score A; the ones with risky patterns are listed below, with what triggered the score.

  • 839 scanned
  • Scanned Nov 17, 2026
  • Static scan, not a runtime audit

What the scan looks at

The scan reads the skill’s public SKILL.md text — the file you would install — and looks for patterns that deserve a second look before you run something an agent will follow:

  • Piped shell downloads (curl … | bash) and other fetch-and-execute patterns.
  • Recursive deletes (rm -rf) and destructive file operations.
  • Dynamic execution (eval, exec, new Function).
  • Base64 decoding of embedded payloads.
  • Credential access: .ssh, id_rsa, .env, cloud and API keys.
  • Safety bypasses: --dangerously-skip-permissions, --no-sandbox.
  • Process spawning and outbound network calls.
  • sudo and world-writable permissions (chmod 777).

Each finding subtracts points from 100. A ≥ 90, B ≥ 75, C ≥ 60, D ≥ 40, F < 40.

What it does not do

It is a static text scan, not a runtime audit. A skill can score A and still behave badly, and a skill can score C for a pattern that is perfectly fine in its context (a browser tool that calls curl on purpose). The grade is a prompt to read the source, not a verdict.

We do not execute skills to grade them, we do not scan bundled script files that are not in the SKILL.md, and we re-scan only when we re-index a skill.

How to read a grade

  • A — no risky patterns found in the text.
  • B / C — one or more patterns found; open the SKILL.md and check whether they are intentional.
  • D — several serious patterns together; read the entire file before installing.

Corrections

If you think a grade is wrong, tell us on the contact page with the skill and the line you are looking at.

Distribution

Grades across the index

5 grades
  • A801
  • B19
  • C18
  • D1
  • F0
Watchlist

Skills below grade A

Read before installing
  1. D sandbox-agent rivet-dev 44/100 pipes a download straight into a shell; reads credential files or secret env vars; makes outbound network calls
  2. C sentry-create-alert getsentry 60/100 pipes a download straight into a shell; makes outbound network calls
  3. C claude-api Anthropic 60/100 reads credential files or secret env vars; executes dynamically built code; makes outbound network calls
  4. C higgsfield-generate Higgsfield AI 66/100 pipes a download straight into a shell; makes outbound network calls
  5. C stripe-projects Stripe 66/100 pipes a download straight into a shell; makes outbound network calls
  6. C canghe-post-to-wechat freestylefly 68/100 pipes a download straight into a shell; makes outbound network calls
  7. C canghe-post-to-x freestylefly 68/100 pipes a download straight into a shell; makes outbound network calls
  8. C google-agents-cli-adk-code Google 68/100 pipes a download straight into a shell; makes outbound network calls
  9. C higgsfield-brandkit Higgsfield AI 68/100 pipes a download straight into a shell; makes outbound network calls
  10. C higgsfield-marketplace-cards Higgsfield AI 68/100 pipes a download straight into a shell; makes outbound network calls
  11. C higgsfield-product-photoshoot Higgsfield AI 68/100 pipes a download straight into a shell; makes outbound network calls
  12. C higgsfield-soul-id Higgsfield AI 68/100 pipes a download straight into a shell; makes outbound network calls
  13. C higgsfield-websites Higgsfield AI 68/100 pipes a download straight into a shell; makes outbound network calls
  14. C higgsfield-youtube-thumbnail Higgsfield AI 68/100 pipes a download straight into a shell; makes outbound network calls
  15. C slack-cli slackapi 68/100 pipes a download straight into a shell; makes outbound network calls
  16. C tdd-workflow affaan-m 68/100 pipes a download straight into a shell; makes outbound network calls
  17. C huawei-cloud-find-skills huaweicloud 72/100 asks for sudo; makes outbound network calls; spawns system processes
  18. C caveman-setup juliusbrussee 74/100 reads credential files or secret env vars; makes outbound network calls
  19. C security-review affaan-m 74/100 reads credential files or secret env vars; makes outbound network calls
  20. B neon-ai-gateway Neon 80/100 reads credential files or secret env vars; makes outbound network calls
  21. B create-slack-app slackapi 82/100 reads credential files or secret env vars
  22. B canghe-image-gen freestylefly 82/100 reads credential files or secret env vars
  23. B convex-create-component Convex 82/100 reads credential files or secret env vars
  24. B durable-objects Cloudflare 82/100 executes dynamically built code; makes outbound network calls
  25. B golang-continuous-integration samber 82/100 reads credential files or secret env vars
  26. B neon-object-storage Neon 82/100 reads credential files or secret env vars
  27. B turnstile-spin Cloudflare 82/100 asks for sudo; makes outbound network calls
  28. B i-have-adhd ayghri 85/100 recursive force delete
  29. B capacitor-app-spm-migration capawesome-team 85/100 recursive force delete
  30. B book-to-skill virgiliojr94 85/100 recursive force delete
  31. B capacitor-app-creation capawesome-team 85/100 recursive force delete
  32. B google-agents-cli-workflow Google 86/100 executes dynamically built code; makes outbound network calls
  33. B security-and-hardening Addy Osmani 88/100 executes dynamically built code
  34. B google-agents-cli-eval Google 88/100 executes dynamically built code
  35. B okx-agent-payments-protocol okx 88/100 decodes base64 payloads; makes outbound network calls
  36. B sandbox-migrate-to-next Cloudflare 88/100 executes dynamically built code
  37. B sandbox-next Cloudflare 88/100 executes dynamically built code
  38. B sandbox-stable Cloudflare 88/100 executes dynamically built code

Community notes

Found a broken install? Know a skill we missed?

One line is enough: the skill name, what happened, and the command you ran. We read every note and fix the index.