Skills python-executor
📦
python-executor
Content revision r1 High Risk ⚙️ External commands🌐 Network access
Run Python Code in a Sandbox
Users often need Python libraries that are unavailable in their local AI tool. This skill runs Python code through an external sandbox and returns text output or generated files.
Supports: Claude Codex Code(CC)
Stop for confirmation before installing.
Review the plan and obtain explicit user consent before changing files.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Agent request
Review the Skillstore skill "python-executor" from https://skillstore.io/skills/halt-catch-fire-python-executor.md and its manifest at https://skillstore.io/api/skills/halt-catch-fire-python-executor/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "python-executor". A sales table needs a short summary and a chart file.
Expected outcome:
- The response includes a printed sales summary with totals and averages.
- A chart file is returned from the outputs folder.
Using "python-executor". A developer needs public profile data from an approved API endpoint.
Expected outcome:
The response returns formatted fields from the API response and notes the outbound network request.
Using "python-executor". A team needs a simple generated image for a report.
Expected outcome:
The response returns a generated image file and a short note describing how it was created.
Security Audit
High Riskv3 • 7/6/2026 Open versioned report
Many static backtick findings are Markdown formatting or library-name false positives. Real concerns remain because the skill authorizes the belt CLI, runs arbitrary Python in an external sandbox, and includes outbound HTTP examples. No prompt injection text was found in SKILL.md.
1
Files scanned
188
Lines analyzed
18
Review items
0
False positives ignored
Confirmed security concerns (1)
High
Remote Python Execution Through External CLI
The skill grants Bash access to belt and directs use of belt app run to execute arbitrary Python. Submitted code and inputs cross into an external sandbox that can also perform network-enabled automation.
The allowed-tools front matter permits Bash(belt *), and the quick start shows belt app run executing supplied Python code. This is explicit remote execution behavior, not an inferred pattern.
Capability review items (18)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Medium
Ruby/shell backtick execution
> **Install the belt CLI skill:** `npx skills add belt-sh/cli`
The documentation instructs installation through npx, which is an external command and supply-chain boundary if followed. It is user-visible rather than hidden, so the risk is moderate.
Medium
Ruby/shell backtick execution
> Requires inference.sh CLI (`belt`). [Install instructions](https://raw.githubusercontent.com/infer
The line directs users to install or configure the external belt CLI before execution. This is an expected dependency, but it expands the trust boundary outside the skill.
Medium
Ruby/shell backtick execution
```bash
The span contains bash commands for belt login and belt app run, which execute submitted Python through an external CLI. This is intended behavior but remains a real external command surface.
Medium
Ruby/shell backtick execution
```bash
The example invokes belt app run from bash to execute a web scraping script. The command is documented, but it still causes external command execution when used.
Medium
Ruby/shell backtick execution
```bash
The example invokes belt app run from bash to execute a data visualization script. This is legitimate usage, but it confirms the external CLI execution pattern.
Medium
Ruby/shell backtick execution
```bash
The example invokes belt app run from bash to execute image processing code. This is documented functionality, but it still depends on external command execution.
Medium
Ruby/shell backtick execution
```bash
The example invokes belt app run from bash for video generation with an extended timeout. This is intended, but it is a real external execution path.
Medium
Ruby/shell backtick execution
```bash
The example invokes belt app run from bash to execute 3D model generation code. This confirms external CLI execution even though the example is not hidden.
Medium
Ruby/shell backtick execution
```bash
The example invokes belt app run from bash and executes Python that calls an external API. This combines external command execution with outbound network access.
Medium
Ruby/shell backtick execution
```bash
The variants section documents belt app run commands, including a high-memory target. These are legitimate examples but confirm external CLI execution.
Medium
Ruby/shell backtick execution
```bash
The related skills section instructs npx skills add for additional packages. This is a visible install command and creates a supply-chain risk if followed automatically.
Low
Python HTTP libraries
"code": "import requests\nfrom bs4 import BeautifulSoup\n\nresponse = requests.get(\"https://example
The example imports requests and fetches https://example.com, so outbound HTTP is an actual demonstrated capability. The target is benign, but network access is real.
Low
Python HTTP libraries
"code": "import requests\nimport json\n\nresponse = requests.get(\"https://api.github.com/users/octo
The example imports requests and calls the GitHub API, demonstrating outbound HTTP from executed Python. This is legitimate but should be disclosed to users.
Low
Hardcoded URL
description: "Execute Python code in a safe sandboxed environment via [inference.sh](https://inferen
The description ties execution to inference.sh, which is an external service dependency. This is not malicious, but it creates a network trust boundary.
Low
Hardcoded URL
. [Install instructions](https://raw.githubusercontent.com/infer
The install instructions link to raw GitHub content for an external CLI dependency. The action is user-controlled, but the network and supply-chain boundary is real.
Low
Hardcoded URL
"code": "import requests\nfrom bs4 import BeautifulSoup\n\nresponse = requests.get(\"https://example
The web scraping example contains a hardcoded external URL and fetches it with requests. This is a benign example but confirms outbound network behavior.
Low
Hardcoded URL
"code": "import requests\nimport json\n\nresponse = requests.get(\"https://api.github.com/users/octo
The API example contains a hardcoded GitHub API URL and fetches it with requests. This is expected functionality but still a real network action.
Risk Factors
⚙️ External commands (41)
SKILL.md:7 SKILL.md:17 SKILL.md:19-26 SKILL.md:26-33 SKILL.md:33-40 SKILL.md:40-47 SKILL.md:47-52 SKILL.md:52 SKILL.md:53 SKILL.md:54 SKILL.md:55-58 SKILL.md:58 SKILL.md:59 SKILL.md:62 SKILL.md:63 SKILL.md:66-67 SKILL.md:67 SKILL.md:68-71 SKILL.md:71 SKILL.md:72 SKILL.md:75 SKILL.md:76 SKILL.md:82-86 SKILL.md:86-90 SKILL.md:90-94 SKILL.md:94-98 SKILL.md:98-102 SKILL.md:102-106 SKILL.md:106-111 SKILL.md:111-115 SKILL.md:115-119 SKILL.md:119-123 SKILL.md:123-127 SKILL.md:127-131 SKILL.md:131-133 SKILL.md:133-139 SKILL.md:139-143 SKILL.md:143-149 SKILL.md:149-166 SKILL.md:166 SKILL.md:171-180
🌐 Network access (10)
Audited by: codex View Audit History →
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/halt-catch-fire-python-executor/audits/3?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/halt-catch-fire-python-executor?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/halt-catch-fire-python-executor?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/halt-catch-fire-python-executor/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/halt-catch-fire-python-executor.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
halt-catch-fire. (2026). python-executor security audit report (audit version 3) [Author version unspecified]. Skillstore. https://skillstore.io/skills/halt-catch-fire-python-executor/audits/3BibTeX citation
@techreport{halt-catch-fire-halt-catch-fire-python-executor-2026,
author = {halt-catch-fire},
title = {python-executor security audit report (audit version 3)},
institution = {Skillstore},
year = {2026},
number = {3},
url = {https://skillstore.io/skills/halt-catch-fire-python-executor/audits/3},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "python-executor security audit report (audit version 3)"
version: "unspecified"
type: report
authors:
- name: "halt-catch-fire"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/halt-catch-fire-python-executor/audits/3"
identifiers:
- type: other
value: "skillstore:halt-catch-fire-python-executor:audit:3"
description: "Skillstore immutable audit report identifier"
Compare variants
10 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
Higher Skillstore usage
Author / source Skillstore Score Evidence Confidence Skillstore usage Updated
infsh-skills Recommended
infsh-skills-python-executor
Skillstore Score 50
Evidence Confidence High
Skillstore usage 41
Updated
2026-09-09
inferen-sh-python-executor
Skillstore Score 50
Evidence Confidence High
Skillstore usage 10
Updated
2026-09-09
101-skills-python-executor
Skillstore Score 50
Evidence Confidence Medium
Skillstore usage 35
Updated
2026-09-09
qu-skills-python-executor
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 56
Updated
2026-09-09
skillssh-python-executor
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 45
Updated
2026-09-09
inference-sh-python-executor
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 43
Updated
2026-09-09
inference-skills-python-executor
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 39
Updated
2026-09-09
inference-sh-9-python-executor
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 39
Updated
2026-09-09
halt-catch-fire Current
halt-catch-fire-python-executor
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 39
Updated
2026-09-09
inference-sh-skills-python-executor
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 38
Updated
2026-09-09
Skillstore Score
Why this score Evidence Confidence: Medium 55
Architecture
85
Maintainability
87
Content
67
Community
83
Spec Compliance
What You Can Build
Analyze Data Tables
Run pandas and visualization tasks when a local Python environment is unavailable.
Automate Developer Tasks
Execute short Python scripts for parsing, transformation, API checks, and repeatable utility work.
Generate Media Files
Create images, videos, PDFs, and 3D files from scripted workflows.
Try These Prompts
Run a Basic Calculation
Use python-executor to run a short Python calculation and show the printed result. Keep the code simple and explain the output.
Create a Chart
Use python-executor to analyze this table and create a bar chart saved under outputs. Return the summary and the generated file.
Process Website Data
Use python-executor to fetch the approved public page, extract the main table, and return a clean CSV file under outputs.
Build a Multi-Step Pipeline
Use python-executor to run a complete pipeline that cleans input data, creates a chart, exports a report, and uses a clear timeout.
Best Practices
- Review code before running it, especially when it sends network requests or handles sensitive data.
- Save generated files under outputs so the executor can return them.
- Use clear timeouts and smaller test inputs before running large jobs.
Avoid
- Do not use it to run untrusted code without approval.
- Do not paste secrets, private data, or credentials into external execution jobs.
- Do not rely on interactive prompts, windows, or display calls for results.
Frequently Asked Questions
Does this run Python code locally?
No. The skill uses the belt CLI to run code through an inference.sh sandbox.
What setup is required?
The documented workflow requires the belt CLI and an inference.sh login or configured account.
Can it make network requests?
Yes. The examples include website and API requests, so outbound network actions should be approved first.
How are generated files returned?
Files saved under outputs are detected and returned by the executor.
Does it support GPU workloads?
No. The skill documents a CPU-only Python 3.10 environment.
Is it safe for sensitive data?
Treat external execution as sensitive. Remove secrets and get approval before sending private data.
Developer Details
Author
halt-catch-fireLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
a06681402992ceae98ba04d54cfd4ab004862696
Maintenance freshness
7/18/2026
Usage
3 downloads · 0 views
File structure
📄 SKILL.md