Works with the AI Agents you already use
Shell Script Admin Safety Reviewer
Review bash and zsh admin scripts for safer quoting, input handling, permissions, and rollout readiness.
$19.99
Shell Script Admin Safety Reviewer
Example session with this skill installed
Review this script for risks before I deploy it via Jamf: it takes $user_input to clear a cache and writes a log to /tmp/log.sh. Give me a verdict and fix snippets.
- Read your context and instructions
- Compiled the shell script admin
Verdict: CAUTION
[Line 14] Finding: Unquoted variable '$user_input' in 'rm -rf'. Risk: Globbing/Word-splitting.
Fix: rm -rf -- "$user_input"
[Line 22] Finding: World-readable temp file in /tmp.
Fix: Use 'mktemp -t script.XXXXXX'.
Rollback: Revert via 'jamf policy -event undo-config'.
Connects securely to your tools. The creator never sees your data.
About this skill
Defensive review for admin shell scripts
Shell Script Admin Safety Reviewer reviews bash, zsh, and sh admin scripts before deployment. It focuses on maintainable fixes for quoting, input handling, permissions, temporary files, logging, and rollout readiness.
What it checks
- Word splitting, globbing, and command substitution mistakes.
- User input, path, and argument validation.
- Root context, sudo usage, umask, ownership, and file permissions.
- Temporary file hygiene, cleanup, and predictable path concerns.
- Logging patterns that may expose sensitive input.
Boundaries
This is a defensive review tool for authorized scripts. Use redacted examples when private values are present. It does not provide unauthorized access guidance.
Output
You get a ready, caution, or hold verdict, line-focused findings, safer replacement snippets, test cases, and rollback notes.
- Does not perform live environment testing or dynamic analysis.
- Cannot detect logic errors in non-standard third-party CLI tools.
- Limited effectiveness on obfuscated or minified scripts.
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