Skills wizard
📦
wizard
Content revision r2 High Risk ⚙️ External commands🌐 Network access📁 Filesystem access🔑 Env variables
Build Guided Bash Setup Wizards
Manual setup and migration procedures are easy to miss or repeat incorrectly. This skill creates interactive Bash wizards with guided stages, confirmations, and value handling.
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 "wizard" from https://skillstore.io/skills/mattpocock-wizard.md and its manifest at https://skillstore.io/api/skills/mattpocock-wizard/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 "wizard". Create a wizard for Stripe test credentials in local development and GitHub Actions.
Expected outcome:
- A Stripe API key stage opens the test dashboard and identifies both required keys.
- The secret prompt hides input, while the publishable key uses visible input.
- Both values update the environment file, and the secret also updates GitHub Actions.
Using "wizard". Plan a wizard for moving an application from staging to production.
Expected outcome:
- The plan lists preparation, data migration, verification, traffic change, and final checks.
- Each irreversible stage includes a confirmation gate and clear success criteria.
- Unknown provider steps are marked for documentation review before script generation.
Using "wizard". Generate a repeatable onboarding wizard from this repository.
Expected outcome:
- The wizard maps example environment variables and CI references without exposing existing values.
- It groups related actions into focused stages with progress estimates.
- The handoff includes syntax validation and the command needed to start the wizard.
Security Audit
High Riskv4 • 7/23/2026 Open versioned report
Most command and device-file alerts are false positives caused by Markdown code spans, arithmetic expansion, fixed commands, and output redirection. Confirmed risks involve intentional environment-secret handling, authenticated GitHub configuration updates, and temporary storage of environment contents. No prompt injection or credential exfiltration intent was found.
2
Files scanned
258
Lines analyzed
4
Review items
0
False positives ignored
Confirmed security concerns (9)
High
Environment file access
description: Generate an interactive bash wizard that walks a human through a manual procedure — thi
The declared capability explicitly captures values and writes environment files and GitHub Actions secrets. This is legitimate but security-sensitive credential handling.
High
Environment file access
A **wizard** is a bash script that walks a human, step by step, through a manual procedure that's te
The skill states that generated wizards capture values and write them to .env and GitHub secrets. Mishandling these values could expose credentials.
High
Environment file access
The delightful UX is already solved by [template.sh](template.sh) — progress with time-remaining, co
The documented template performs idempotent .env updates and GitHub secret writes. These are real sensitive-file and remote credential operations.
High
Environment file access
- For setup: `.env`, `.env.example`, `.env.*`, `README`, `docker-compose*`, framework config, and `.
The instructions direct the agent to inspect populated .env variants and CI secret references. Reading populated files can place existing credentials into model context.
High
Environment file access
**Done when:** every stage is named in order, and for each captured value you know (a) where the hum
The workflow requires mapping captured values to .env or GitHub secret destinations and classifying secrecy. This confirms intentional handling of sensitive configuration.
High
Environment file access
ENV_FILE="${ENV_FILE:-.env}"
ENV_FILE selects the file later read and replaced by helper functions, defaulting to .env. The environment override can redirect sensitive reads and writes to another path.
High
Environment file access
# ask KEY "Prompt" — read a value into $KEY. Offers the existing .env value as
The documented ask behavior retrieves an existing .env value for reuse, and ask_secret uses the same path. This intentionally reads potentially sensitive credentials.
Medium
Environment Value Injection
write_env appends values without rejecting embedded newlines. A pasted multiline value can add or replace unintended environment assignments.
The value is written directly through printf, and Bash input can contain embedded newlines. No validation or dotenv escaping occurs before replacement.
Show all 9 confirmed findings
Medium
Unscoped GitHub Configuration Writes
set_secret and set_var mutate the repository inferred by gh without displaying or validating it. A wrong working directory can update another repository.
Both helpers invoke authenticated gh mutation commands without an explicit repository argument or repository confirmation. The target therefore depends on ambient CLI context.
Capability review items (4)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
High
Generic API/secret keys
ask_secret STRIPE_SECRET_KEY "Paste the secret key:"
The script intentionally captures a Stripe secret key into a shell variable. Hidden input protects display but the credential remains sensitive in process memory.
High
Generic API/secret keys
write_env STRIPE_SECRET_KEY "$STRIPE_SECRET_KEY"
The captured Stripe secret key is persisted in a plaintext environment file. File disclosure or accidental version control inclusion could expose the credential.
High
Generic API/secret keys
set_secret STRIPE_SECRET_KEY "$STRIPE_SECRET_KEY" # CI needs this one
The script sends the captured credential to GitHub through an authenticated gh secret command. This is an intentional remote secret mutation with meaningful impact.
Low
Temp file creation
tmp=$(mktemp)
The temporary file receives the complete environment-file contents and a new value. No cleanup trap removes this credential-bearing file if a later command fails.
Risk Factors
⚙️ External commands (20)
🌐 Network access (1)
📁 Filesystem access (12)
🔑 Env variables (3)
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/mattpocock-wizard/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/mattpocock-wizard?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/mattpocock-wizard?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/mattpocock-wizard/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/mattpocock-wizard.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
mattpocock. (2026). wizard security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/mattpocock-wizard/audits/4BibTeX citation
@techreport{mattpocock-mattpocock-wizard-2026,
author = {mattpocock},
title = {wizard security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/mattpocock-wizard/audits/4},
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: "wizard security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
- name: "mattpocock"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/mattpocock-wizard/audits/4"
identifiers:
- type: other
value: "skillstore:mattpocock-wizard:audit:4"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: Medium 55
Architecture
85
Maintainability
87
Content
67
Community
83
Spec Compliance
What You Can Build
Standardize Project Onboarding
Create a repeatable wizard that collects configuration values and guides each setup stage.
Configure Third-Party Services
Guide dashboard navigation, capture service credentials, and place values in approved destinations.
Control One-Time Migrations
Turn a state transition into ordered stages with confirmation before irreversible actions.
Try These Prompts
Create a Basic Wizard
Create a Bash wizard for [procedure]. Include these stages: [stages]. Save captured values to [destination]. Ask before irreversible actions.
Set Up a Service
Build a wizard for [service]. Open the required dashboard pages. Capture [values]. Store secrets locally and in GitHub only where required.
Map Repository Configuration
Review this repository for setup requirements. Propose ordered wizard stages and value destinations. Wait for approval before generating the script.
Design a Migration Wizard
Create a wizard that moves [system] from [current state] to [target state]. Include validation, rollback guidance, confirmations, and a final completion summary.
Best Practices
- Confirm the stage plan and every value destination before generating the wizard.
- Use hidden input for secrets and write only credentials required by each destination.
- Verify syntax statically and review every remote or irreversible action with the user.
Avoid
- Do not invent dashboard steps when current provider documentation is unavailable.
- Do not place secrets in visible prompts, logs, examples, or command arguments.
- Do not run the interactive wizard end to end without the user controlling each stage.
Frequently Asked Questions
What does this skill generate?
It generates an interactive Bash script that guides a person through setup, migration, or state-change stages.
Can the wizard store secrets?
Yes. It can capture hidden input, update an environment file, and set GitHub Actions secrets through gh.
Does it run without human input?
No. The workflow opens browser pages, waits for copied values, and asks for confirmations.
Which operating systems can open URLs?
The template supports common browser commands on Windows, WSL, Linux, and macOS.
Does GitHub configuration always work?
No. The gh CLI must be installed, authenticated, and connected to the intended repository.
How should generated scripts be verified?
Check Bash syntax, run ShellCheck when available, and trace every captured value to its approved destination.
Developer Details
Author
mattpocockLicense
MIT
Skillstore revision
r2
Version notice
The author did not declare a version.
Ref
ebdfe608f5de2b66ff37ab4af12af8ac4f5e8006
Maintenance freshness
7/25/2026
Usage
3 downloads · 0 views
File structure
📄 SKILL.md