Sandboxed Python execution via inference.sh
Run Python code in a sandboxed cloud environment — 100+ pre-installed libraries, file outputs returned automatically
- What
- Run Python code in a sandboxed cloud environment — 100+ pre-installed libraries, file outputs returned automatically
- Cost
- Free
- Needs
- review the source repository first — it declares no license, so reuse terms are unconfirmed; an inference.sh account and the `belt` CLI are required (commercial service — check pricing). ⚠️ The documented install pipes `curl -fsSL https://cli.inference.sh | sh` — the source also documents a manual checksum-verified install; review both before running anything.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
⚠️ Security warning — this skill requires the `belt` CLI, whose documented install runs `curl -fsSL https://cli.inference.sh | sh`; the source also documents a manual checksum-verified install — review before running either. 💳 Paid service — inference.sh is a commercial platform (code runs on their infrastructure); no free tier is confirmed in the source — check pricing and terms. Curated by Skill Harbor — a short pointer to @bankai-skills' guide for executing Python code in a sandboxed cloud environment: Python 3.10, CPU-only, 8 GB RAM (16 GB variant), 1–300 s timeouts, 100+ pre-installed libraries (NumPy, pandas, matplotlib, requests, BeautifulSoup, Selenium, Playwright, MoviePy, Pillow, OpenCV, trimesh, reportlab…), with files saved to `outputs/` returned automatically. Honest caveats: no license declared in the repository — license unknown, so this is a short fiche linking to the source, without reusing its content; non-interactive and CPU-only — no GPU/ML workloads, use dedicated AI apps for those; a metered commercial sandbox, not a free local interpreter. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Sandboxed Python execution via inference.sh is a free Muse skill pointing to the guide for running Python code in a sandboxed cloud environment. It offers Python 3.10, CPU-only, 8 GB of RAM with a 16 GB variant, 1-to-300-second timeouts, and over 100 pre-installed libraries, with file outputs returned automatically. Inference.sh is a paid service, so check pricing first.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit becc256Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: review the source repository first — it declares no license, so reuse terms are unconfirmed; an inference.sh account and the `belt` CLI are required (commercial service — check pricing). ⚠️ The documented install pipes `curl -fsSL https://cli.inference.sh | sh` — the source also documents a manual checksum-verified install; review both before running anything. Open the source of "Sandboxed Python execution via inference.sh" for me: Repository: https://raw.githubusercontent.com/bankai-skills/superpowers/becc25649700d5457772a00e5143e28ccf9e5afa/tools/utilities/python-executor/SKILL.md Pinned version: install the code at commit becc25649700d5457772a00e5143e28ccf9e5afa exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file from the repository into a temporary folder 2. Read it as a guide only — it carries no declared license, so don't copy its text into other files. 3. Report what it covers and how to use it. GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it. Rules: don't touch anything outside the temp folder. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
- It can contact outside services over the network.
What the scan found — excerpts from the install prompt
- makes network calls — Prerequisites: review the source repository first — it declares no license, so reuse terms are unconfirmed; an · Prérequis : examiner d'abord le dépôt source — il ne déclare aucune licence, les conditions de réutilisation s
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- becc256 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : makes network calls
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.