- Home
- Skills
- Code Quality & Review
- Jamf Script Safety Reviewer
Works with the AI Agents you already use
Jamf Script Safety Reviewer
Review Jamf and Kandji scripts for safer user context, prompts, logging, and rollout readiness.
$49.99
Jamf Script Safety Reviewer
Example session with this skill installed
Review my Jamf policy script for user context errors and security issues before I deploy it. Here is the code using whoami and a hardcoded bearer token for the API.
- Read your context and instructions
- Compiled the jamf script safety
Verdict: CAUTION
Issue: Script uses 'whoami' which returns 'root' in Jamf policies, breaking user-path logic.
Fix: Use stat -f %Su /dev/console to capture the current GUI user.
Security: Flagged hardcoded API bearer token; replacing with a recommended token-rotation logic block.
Connects securely to your tools. The creator never sees your data.
About this skill
Defensive script review for Mac admins
Jamf Script Safety Reviewer reviews Jamf Pro, Self Service, Kandji, and Iru scripts before production rollout. It focuses on user context, prompt behavior, logging hygiene, shell robustness, and staged deployment planning.
What it checks
- Console-user detection and root-versus-user assumptions.
- Prompt patterns that may expose sensitive input in logs, files, or process listings.
- Jamf API token handling from redacted examples.
- Quoting, PATH assumptions, temp files, cleanup, and rollback readiness.
- Kandji and Iru adaptation notes for migrated workflows.
Boundaries
This is a defensive admin-review skill. Use redacted or synthetic examples. It does not collect, validate, store, transmit, or request live passwords, tokens, recovery keys, or private tenant values.
Output
You get a ready, caution, or hold verdict, specific findings, safer replacement patterns, test steps, and rollout notes.
- Cannot execute or live-test scripts.
- Reviews redacted/synthetic code only; no live credential validation.
- Does not interface directly with MDM APIs or tenant environments.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 5 months ago
Permissions
No special permissions declared or detected