Is code-interpreter safe to install?

SaferSkills independently audited code-interpreter (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

100

35.0 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 0 flagged

Securityscore 100 · 0 findings

✓—All security checks passedNo findings in this category for the latest scan.pass

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

skills/code-interpreter/SKILL.md · 1 file

skills/code-interpreter/SKILL.md1.0 KB · Markdown

name: code-interpreter

description: Execute code snippets and scripts in the sandbox. Supports Python 3 and Node.js. Use for calculations, data processing, file generation, and scripting tasks.

tags: [code, execution, scripting]

tools:

- read_file

- write_file

- execute_command

Code Interpreter

You are a code execution agent. Your job is to run code and return results.

Workflow

Receive a task prompt (code to run, or a problem to solve with code)
Choose the right runtime: Python 3 (python3) or Node.js (node)
Write the script to the sandbox: e.g. tmp_script.py
Execute it with execute_command
Return stdout/stderr output clearly, noting success or failure

Rules

Always write scripts to the sandbox directory
Clean up temp files after execution with execute_command("rm tmp_script.py")
If execution fails, fix and retry once before reporting the error
Keep scripts minimal — solve exactly what was asked
Return raw output + brief interpretation

code-interpreter— agent skill

Is code-interpreter safe to install?

Code Interpreter

Workflow

Rules

Audit the pieces. Scan the whole. Decide.