Skills python-executor
📦
python-executor
Content revision r1 High Risk ⚙️ External commands🌐 Network access
Run Python Code in a Sandbox
Agents often need Python execution without managing local packages. This skill runs scripts through inference.sh with common data, web, media, and document libraries.
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/skillssh-python-executor.md and its manifest at https://skillstore.io/api/skills/skillssh-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". Create a bar chart from a small sales table and save it as a file.
Expected outcome:
A chart file is returned from the outputs folder, with a short note naming the file.
Using "python-executor". Fetch public profile data from an approved API and summarize key fields.
Expected outcome:
- The response includes a concise summary of the public data.
- Any requested report file is returned from outputs.
Using "python-executor". Convert a simple 3D object into an exportable model file.
Expected outcome:
A model file is returned from outputs, along with basic size and geometry notes.
Security Audit
High Riskv5 • 7/7/2026 Open versioned report
Most markdown backtick findings are false positives from fenced examples and package names. Several infsh app run examples are intentional external command execution, and the skill has real network-capable examples. No prompt injection evidence was found.
1
Files scanned
186
Lines analyzed
14
Review items
0
False positives ignored
Confirmed security concerns (1)
High
Arbitrary Python Execution Through External CLI
The skill grants Bash access to infsh and instructs agents to submit arbitrary Python code to infsh/python-executor. This sends code and possible data to an external execution service.
The allowed-tools declaration permits Bash(infsh *), and examples submit a code field to infsh/python-executor. The risk is inherent, though execution is described as sandboxed.
Capability review items (14)
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
```bash
This bash block runs infsh login and infsh app run with submitted Python code. It is intentional external command execution and should require user trust.
Medium
Ruby/shell backtick execution
```bash
This bash example invokes infsh app run and executes Python that performs web scraping. The command is intentional but can contact external sites.
Medium
Ruby/shell backtick execution
```bash
This bash example invokes infsh app run to execute Python and write chart output. It is intended external command execution through the CLI.
Medium
Ruby/shell backtick execution
```bash
This bash example invokes infsh app run to execute image-processing Python. It is intended external command execution through the CLI.
Medium
Ruby/shell backtick execution
```bash
This bash example invokes infsh app run for video creation with a long-running Python script. It is intended external command execution through the CLI.
Medium
Ruby/shell backtick execution
```bash
This bash example invokes infsh app run to execute 3D-processing Python. It is intended external command execution through the CLI.
Medium
Ruby/shell backtick execution
```bash
This bash example invokes infsh app run with Python that calls an external API. The command executes user-provided code and performs network access.
Medium
Ruby/shell backtick execution
```bash
This bash block documents infsh app run commands, including the high-memory variant. It is intended external command execution through the CLI.
Medium
Ruby/shell backtick execution
```bash
This bash block suggests npx skills add commands for related skills. Installing additional skills is a real supply-chain action and needs user confirmation.
Low
Python HTTP libraries
"code": "import requests\nfrom bs4 import BeautifulSoup\n\nresponse = requests.get(\"https://example
The example imports requests and performs an HTTP GET to example.com. This is real outbound network behavior, although it is presented as a benign demo.
Low
Python HTTP libraries
"code": "import requests\nimport json\n\nresponse = requests.get(\"https://api.github.com/users/octo
The example imports requests and performs an HTTP GET to the GitHub API. This is real outbound network behavior, although it is presented as a benign demo.
Low
Hardcoded URL
![Python Code Executor](https://cloud.inference.sh/u/33sqbmzt3mrg2xxphnhw5g5ear/01k8d8b4mckh6z89dhtx
The Markdown image uses an external cloud.inference.sh URL. Rendering it may fetch a third-party asset and disclose basic viewer metadata.
Low
Hardcoded URL
"code": "import requests\nfrom bs4 import BeautifulSoup\n\nresponse = requests.get(\"https://example
The hardcoded example.com URL is inside Python code that performs an HTTP request. It is a real, low-risk network example.
Low
Hardcoded URL
"code": "import requests\nimport json\n\nresponse = requests.get(\"https://api.github.com/users/octo
The hardcoded GitHub API URL is inside Python code that performs an HTTP request. It is a real, low-risk network example.
Risk Factors
⚙️ External commands (40)
SKILL.md:15 SKILL.md:17-24 SKILL.md:24-31 SKILL.md:31-38 SKILL.md:38-45 SKILL.md:45-50 SKILL.md:50 SKILL.md:51 SKILL.md:52 SKILL.md:53-56 SKILL.md:56 SKILL.md:57 SKILL.md:60 SKILL.md:61 SKILL.md:64-65 SKILL.md:65 SKILL.md:66-69 SKILL.md:69 SKILL.md:70 SKILL.md:73 SKILL.md:74 SKILL.md:80-84 SKILL.md:84-88 SKILL.md:88-92 SKILL.md:92-96 SKILL.md:96-100 SKILL.md:100-104 SKILL.md:104-109 SKILL.md:109-113 SKILL.md:113-117 SKILL.md:117-121 SKILL.md:121-125 SKILL.md:125-129 SKILL.md:129-131 SKILL.md:131-137 SKILL.md:137-141 SKILL.md:141-147 SKILL.md:147-164 SKILL.md:164 SKILL.md:169-178
🌐 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/skillssh-python-executor/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/skillssh-python-executor?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/skillssh-python-executor?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/skillssh-python-executor/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/skillssh-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
skillssh. (2026). python-executor security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/skillssh-python-executor/audits/5BibTeX citation
@techreport{skillssh-skillssh-python-executor-2026,
author = {skillssh},
title = {python-executor security audit report (audit version 5)},
institution = {Skillstore},
year = {2026},
number = {5},
url = {https://skillstore.io/skills/skillssh-python-executor/audits/5},
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 5)"
version: "unspecified"
type: report
authors:
- name: "skillssh"
date-released: "2026-07-07"
url: "https://skillstore.io/skills/skillssh-python-executor/audits/5"
identifiers:
- type: other
value: "skillstore:skillssh-python-executor:audit:5"
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
inferen-sh Recommended
inferen-sh-python-executor
Skillstore Score 50
Evidence Confidence High
Skillstore usage 9
Updated
2026-08-21
infsh-skills-python-executor
Skillstore Score 50
Evidence Confidence High
Skillstore usage 8
Updated
2026-08-21
101-skills-python-executor
Skillstore Score 50
Evidence Confidence Medium
Skillstore usage 3
Updated
2026-08-21
qu-skills-python-executor
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 22
Updated
2026-08-21
skillssh Current
skillssh-python-executor
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 12
Updated
2026-08-21
inference-sh-python-executor
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 11
Updated
2026-08-21
inference-skills-python-executor
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 7
Updated
2026-08-21
inference-sh-9-python-executor
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 7
Updated
2026-08-21
inference-sh-skills-python-executor
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 6
Updated
2026-08-21
halt-catch-fire-python-executor
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 4
Updated
2026-08-21
Skillstore Score
Why this score Evidence Confidence: Medium 55
Architecture
85
Maintainability
87
Content
68
Community
83
Spec Compliance
What You Can Build
Analyze Small Datasets
Summarize and visualize CSV or table data without preparing a local Python environment.
Prototype Automation Scripts
Test API calls, transformations, and file generation through a managed Python runtime.
Generate Operational Assets
Create charts, PDFs, images, short videos, or converted files for repeatable content tasks.
Try These Prompts
Run a Basic Script
Use python-executor to run a short Python calculation and show the printed result. Keep the default timeout.
Analyze a CSV
Use python-executor to load my CSV, summarize numeric columns, and save one clear chart in outputs.
Create a Media Asset
Use python-executor to create an image or short video from my requirements, then return the output filename.
Automate a Report Workflow
Use python-executor to fetch approved API data, transform it with pandas, create a PDF summary, and return all files.
Best Practices
- Review generated code before execution, especially network and file operations.
- Use the shortest practical timeout and choose high_memory only for large jobs.
- Save durable results under outputs so the skill can return the files.
Avoid
- Do not submit secrets, access tokens, or private datasets without approval for inference.sh processing.
- Do not scrape websites without permission or required compliance checks.
- Do not rely on interactive windows, prompts, or GUI displays.
Frequently Asked Questions
What does this skill do?
It runs Python scripts through the inference.sh python-executor app and returns text or generated files.
Does it run on my local Python install?
No. It uses the infsh CLI to run an inference.sh app, not your local Python interpreter.
Which libraries are available?
It lists common libraries for data analysis, plotting, web scraping, images, video, PDFs, and 3D processing.
Can it create files?
Yes. Files saved under outputs are automatically detected and returned by the app.
Does it support GPU workloads?
No. The documented environment is CPU-only and points users to dedicated AI apps for those workloads.
Is it safe for sensitive data?
Treat submitted code and data as sent to an external service. Use only data approved for that environment.