security-expert
Use when analyzing security vulnerabilities, conducting security reviews, checking for common vulnerabilities, or when the user mentions "security"…
Skill by ntk148v
Chalk Labs
Need help deploying security-expert?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ntk148v-security-expert
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing, security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/security-expert
What's inside
- Skill name
security-expert- Description
- Use when analyzing security vulnerabilities, conducting security reviews, checking for common vulnerabilities, or when the user mentions "security", "vulnerability", "CVE", "OWASP", or "penetration test".
- License
- MIT
- Instructions
- 523 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- body: 523 lines (spec recommends under 500)
Files (1)
- SKILL.md
SKILL.md (first lines)
# Security Expert
## Overview
Security Expert provides a systematic approach to identifying and preventing security vulnerabilities in code. It covers OWASP Top 10, common vulnerability patterns, secure coding practices, and remediation strategies for building secure applications.
## When to Use
Use this skill when:
- Conducting security reviews
- Analyzing code for vulnerabilities
- The user mentions "security", "vulnerability", or "secure coding"
- Checking for OWASP Top 10 issues
- Reviewing authentication and authorization
- Validating input handling
- Investigating potential CVEs
## Security Review Process
### Phase 1: Threat Modeling
Before writing code, understand potential threats:
1. **Identify Assets**
- User data (PII, credentials)
- Financial information
- Intellectual property
- System access
2. **Map Attack Surface**
- User inputs (forms, APIs, URLs)
- External services
- File uploads
- Configuration files
3. **Identify Attack Vectors**
- SQL injection
- Cross-site scripting (XSS)
- Cross-site request forgery (CSRF)
- Authentication bypass
- Authorization flaws
### Phase 2: Input Validation
All user input is evil until proven otherwise.
#### SQL Injection
**The Problem:**
```sql
-- User input directly concatenated
SELECT * FROM users WHERE id = ${userId}
-- Attacker input: 1; DROP TABLE users;--
```
**The Solution - Parameterized Queries:**
```javascript
// ❌ BAD: String concatenation
const query = `SELECT * FROM users WHERE id = ${userId}`;
// ✅ GOOD: Parameterized query
const query = "SELECT * FROM users WHERE id = ?";
db.query(query, [userId]);
```
```python
# ❌ BAD: String formatting
cursor.execute(f"SELECT * FROM users WHERE id = {user_id}")
# ✅ GOOD: Parameterized query
cursor.execute("SELECT * FROM users WHERE id = %s", (user_id,))
```
#### Command Injection
```javascript
// ❌ BAD: User input in shell command
const cmd = `ls ${userDirectory}`;
exec(cmd);
// ✅ GOOD: Avoid shell when possible, or use safe alternatives
const files = fs.readdirSync(userDirectory);
```
```python
# ❌ BAD: shell=True with user input
subprocess.run(f"ls {directory}", shell=True)
# ✅ GOOD: list form without shell
subprocess.run(["ls", directory])
```
#### Path Traversal
```javascript
// ❌ BAD: User input in file path
const file = path.join uploadsDir, req.body.filename;
fs.readFile(file);
// ✅ GOOD: Validate and sanitize
const filename = req.body.filename;
if (!isValidFilename(filename)) {
throw new Error('Invalid filename');
}
const file = path.join(uploadsDir, filename);
if (!file.startsWith(uploadsDir)) {
throw new Error('Path traversal detected');
}
```
### Phase 3: Authentication & Authorization
#### Password Security
```javascriptFrom ntk148v/skills, MIT.
More from ntk148v/skills
- 0.497score
skill-authoring
ntk148v
Use when creating, editing, auditing, or validating Agent Skills.
SkillCFreshness: C★ 1Claude Code +9 - 0.493score
repo-analyzer
ntk148v
Use when the user mentions "analyzing a project", "analyzing a repository", "analyzing GitHub", "project analysis", "source code analysis", "architecture…
SkillCFreshness: C★ 1Claude Code +9 - 0.472score
caveman
ntk148v
Ultra-compressed communication mode.
SkillCFreshness: C★ 1Claude Code +9 - 0.467score
grill
ntk148v
Interview the user relentlessly about a plan, design, or domain model until reaching shared understanding.
SkillCFreshness: C★ 1Claude Code +9 - 0.461score
handoff
ntk148v
Compact the current conversation into a handoff document for another agent to pick up.
SkillCFreshness: C★ 1Claude Code +9 - 0.432score
conventional-commits
ntk148v
Use when creating git commits, writing commit messages, or when the user mentions conventional commits, semantic versioning, or automated changelog generation.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
code-reviewer
ntk148v
Use when reviewing code, conducting code reviews, analyzing pull requests, or when the user mentions "code review", "PR review", "code quality", or "static…
SkillDFreshness: D★ 1Claude Code +9 - 0.423score
deep-wiki
ntk148v
Use when generating comprehensive documentation for a codebase, creating wiki pages, documenting architecture, or when the user mentions "deep wiki"…
SkillDFreshness: D★ 1Claude Code +9 - 0.423score
system-performance
ntk148v
Use when analyzing system performance, debugging performance issues, investigating bottlenecks, or when the user mentions "performance analysis", "USE…
SkillDFreshness: D★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Apr 3, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ntk148v/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ntk148v
- 0.497score
skill-authoring
ntk148v
Use when creating, editing, auditing, or validating Agent Skills.
SkillCFreshness: C★ 1Claude Code +9 - 0.493score
repo-analyzer
ntk148v
Use when the user mentions "analyzing a project", "analyzing a repository", "analyzing GitHub", "project analysis", "source code analysis", "architecture…
SkillCFreshness: C★ 1Claude Code +9 - 0.472score
caveman
ntk148v
Ultra-compressed communication mode.
SkillCFreshness: C★ 1Claude Code +9 - 0.467score
grill
ntk148v
Interview the user relentlessly about a plan, design, or domain model until reaching shared understanding.
SkillCFreshness: C★ 1Claude Code +9 - 0.461score
handoff
ntk148v
Compact the current conversation into a handoff document for another agent to pick up.
SkillCFreshness: C★ 1Claude Code +9 - 0.432score
conventional-commits
ntk148v
Use when creating git commits, writing commit messages, or when the user mentions conventional commits, semantic versioning, or automated changelog generation.
SkillDFreshness: D★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get security-expert running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
security-expert skill. Agent Mart. https://agentmart.dev/skills/ntk148v-security-expert (last updated 2026-10-24)