📦

hook

Name: hook
Author: Emz1998

Content revision r1 High Risk ⚙️ External commands📁 Filesystem access🔑 Env variables

Create Claude Code Hooks Safely

Claude Code hooks are powerful but easy to misconfigure. This skill guides hook creation, configuration, validation, and security review.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

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 "hook" from https://skillstore.io/skills/emz1998-hook.md and its manifest at https://skillstore.io/api/skills/emz1998-hook/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.

Markdown detail GET /skills/emz1998-hook.md Signed manifest GET /api/skills/emz1998-hook/manifest Signed lockfile GET /api/skills/emz1998-hook/lockfile

Test it

Using "hook". Create a hook that warns when Bash uses slow search commands.

Expected outcome:

The skill proposes a PreToolUse Bash hook, creates a validator script, links it to local settings, and reports the validation result.

Using "hook". Add a hook that blocks prompts containing secrets.

Expected outcome:

The skill creates a prompt validation workflow, explains the blocked patterns, updates the hook configuration, and lists manual review steps.

Using "hook". Audit my existing hooks before I enable them.

Expected outcome:

The skill reviews hook files and settings, highlights risky commands, checks syntax, and recommends safer matchers or confirmation steps.

Security Audit

High Risk

v4 • 7/5/2026 Open versioned report

Most static findings are documentation examples or Markdown backticks rather than active malicious code. One static issue is confirmed because an example persists an API key in CLAUDE_ENV_FILE. Semantic review found high-impact hook automation risks but no prompt injection attempt.

Files scanned

1,203

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (2)

High

SKILL.md:24 SKILL.md:32 SKILL.md:56 hooks.md:1027-1032

Persistent Hook Command Execution

The workflow creates or updates scripts in .claude/hooks and links them in settings.local.json. The reference also warns that hooks execute arbitrary shell commands and can access user-readable files.

The skill directly instructs the agent to create hook scripts and update hook settings. The reference explicitly states these hooks execute arbitrary shell commands with user file access.

High

hooks.md:675-686 hooks.md:751-766 hooks.md:802-807

Hook-Based Prompt and Permission Control

The reference describes hooks that can approve tool use, modify inputs, block prompts, or add context. Generated hooks using these features can alter the agent workflow if misconfigured.

The cited sections define permission approval, input mutation, prompt blocking, and context injection behavior. These are documented features, but they create high-impact control points.

Capability review items (1)

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

hooks.md:398

Generic API/secret keys

echo 'export API_KEY=your-api-key' >> "$CLAUDE_ENV_FILE"

The example writes API_KEY into CLAUDE_ENV_FILE, which can expose credentials to later hook and shell commands if copied. The value is a placeholder, but the pattern encourages secret persistence.

Risk Factors

⚙️ External commands (13)

hooks.md:412 hooks.md:419 hooks.md:394 hooks.md:410 SKILL.md:16 SKILL.md:17 SKILL.md:18 SKILL.md:24 SKILL.md:32 SKILL.md:47 SKILL.md:52 SKILL.md:56 SKILL.md:68

📁 Filesystem access (26)

🔑 Env variables (1)

hooks.md:398

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.

Open versioned report

Copy report link

https://skillstore.io/skills/emz1998-hook/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/emz1998-hook/security.svg)](https://skillstore.io/skills/emz1998-hook?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/emz1998-hook?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/emz1998-hook/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/emz1998-hook.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

Emz1998. (2026). hook security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/emz1998-hook/audits/4

BibTeX citation

@techreport{emz1998-emz1998-hook-2026,
  author = {Emz1998},
  title = {hook security audit report (audit version 4)},
  institution = {Skillstore},
  year = {2026},
  number = {4},
  url = {https://skillstore.io/skills/emz1998-hook/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: "hook security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
  - name: "Emz1998"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/emz1998-hook/audits/4"
identifiers:
  - type: other
    value: "skillstore:emz1998-hook:audit:4"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Automate Project Checks

Create hooks that run formatters, linters, or validation commands after file edits.

Add Security Guardrails

Build hooks that block unsafe shell commands, sensitive file access, or risky prompts.

Configure Team Workflows

Standardize local hook settings and reusable hook scripts across a project.

Try These Prompts

Create a Basic Hook

Create a PostToolUse hook named format-after-edit. It should run our formatter after Write or Edit and report any safety checks.

Update an Existing Hook

Review the existing hook named protect-main-branch. Add clearer error handling and keep the current branch protection behavior.

Add Prompt Validation

Create a UserPromptSubmit hook that blocks prompts containing secrets, tokens, or private keys. Explain how it is linked and tested.

Design a Hook Policy

Design a hook policy for this repository using PreToolUse, PostToolUse, and Stop events. Include matchers, commands, risks, and validation steps.

Best Practices

Review hook command paths and matchers before enabling them.
Keep hook scripts small, deterministic, and easy to test.
Store secrets outside generated hook code and avoid writing them to environment files.

Avoid

Enabling hooks that auto-approve broad file or shell access.
Hardcoding tokens, API keys, or private paths in hook scripts.
Using Stop hooks that can continue sessions without a termination guard.

Frequently Asked Questions

What does this skill create?

It creates or updates Claude Code hook scripts and links them in local settings.

Can it configure multiple hook events?

Yes. It can select events such as PreToolUse, PostToolUse, UserPromptSubmit, Stop, and SessionStart.

Does it run hooks in a sandbox?

No. Hooks run with normal user permissions, so every command needs review.

Can it help with security checks?

Yes. It can add validation, deny rules, and checks for risky prompts or commands.

Will it store credentials?

It should not store credentials. Users should keep secrets outside hook scripts and environment files.

Is it only for Claude Code?

The workflow is designed for Claude Code hooks and may need changes for other tools.

Developer Details

Author

Emz1998

License

MIT

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/Emz1998/nexly-notes/tree/main/.claude/skills%20copy/hook

Ref

30c73eac2afe762f6aa9c4553158769369d47351

Maintenance freshness

7/18/2026

Usage

5 downloads · 145 views

File structure

📄 hooks.md

📄 SKILL.md