frontend-security

frontend-security is a skill for Claude Code, Codex from schalkneethling/webdev-agent-skills. It costs 89 tokens per session (1,606 once invoked), scanned A, original, MIT.

A security-audit guide for frontend codebases, including browser code and Node.js or npm dependencies. It checks for issues such as cross-site scripting, cross-site request forgery, unsafe DOM use, weak content security policies, poor input handling, and unsafe file uploads.

In plain words
What is it for?
Use it during security reviews to scan for dangerous patterns, check defensive measures, review dependencies, and organize findings by severity with remediation guidance.
Why use it?
It helps find common frontend security weaknesses and missing protections before they become exploitable problems.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it during security reviews to scan for dangerous patterns, check defensive measures, review dependencies, and organize findings by severity with remediation guidance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/schalkneethling/webdev-agent-skills/frontend-security
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add schalkneethling/webdev-agent-skills --skill frontend-security
Clone the repo
git clone --depth 1 https://github.com/schalkneethling/webdev-agent-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for frontend-security

README.md
[![agentmods](https://agentmods.dev/badge/skills/schalkneethling/webdev-agent-skills/frontend-security/github.svg)](https://agentmods.dev/skills/schalkneethling/webdev-agent-skills/frontend-security)
Your own site
<a href="https://agentmods.dev/skills/schalkneethling/webdev-agent-skills/frontend-security"><img src="https://agentmods.dev/badge/skills/schalkneethling/webdev-agent-skills/frontend-security/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for frontend-security

Your own site · 80×15
<a href="https://agentmods.dev/skills/schalkneethling/webdev-agent-skills/frontend-security"><img src="https://agentmods.dev/badge/skills/schalkneethling/webdev-agent-skills/frontend-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,606 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 18 Mar 2026
  • Snyk fail 15 Feb 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00089 $0.01606
Opus 5.5 $0.00036 $0.00642
Sonnet 5.5 $0.00018 $0.00321
Haiku 4.5 $0.00009 $0.00161

Measured 2mo ago against content hash 6ac4708d15b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

frontend-security scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

frontend-security/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frontend Security Audit Skill

Perform comprehensive security audits of frontend codebases to identify vulnerabilities, bad practices, and missing protections.

Audit Process

  1. Scan for dangerous patterns - Search codebase for known vulnerability indicators
  2. Review framework-specific risks - Check for framework security bypass patterns
  3. Validate defensive measures - Verify CSP, CSRF tokens, input validation
  4. Check dependencies - Review npm/node dependencies for vulnerabilities
  5. Report findings - Categorize by severity with remediation guidance

XSS Indicators (Search Priority: HIGH)

# React dangerous patterns
grep -rn "dangerouslySetInnerHTML" --include="*.jsx" --include="*.tsx" --include="*.js"

# Direct DOM manipulation
grep -rn "\.innerHTML\s*=" --include="*.js" --include="*.ts" --include="*.jsx" --include="*.tsx"
grep -rn "\.outerHTML\s*=" --include="*.js" --include="*.ts"
grep -rn "document\.write" --include="*.js" --include="*.ts"

# URL-based injection
grep -rn "location\.href\s*=" --include="*.js" --include="*.ts"
grep -rn "location\.replace" --include="*.js" --include="*.ts"
grep -rn "window\.open" --include="*.js" --include="*.ts"

# Eval and code execution
grep -rn "eval\s*(" --include="*.js" --include="*.ts"
grep -rn "new Function\s*(" --include="*.js" --include="*.ts"
grep -rn "setTimeout\s*(\s*['\"]" --include="*.js" --include="*.ts"
grep -rn "setInterval\s*(\s*['\"]" --include="*.js" --include="*.ts"

# Twig unescaped output
grep -rn "|raw" --include="*.twig" --include="*.html.twig"
grep -rn "{% autoescape false %}" --include="*.twig"

CSRF Indicators

# Forms without CSRF tokens
grep -rn "<form" --include="*.html" --include="*.jsx" --include="*.tsx" --include="*.twig"

# State-changing requests without protection
grep -rn "fetch\s*(" --include="*.js" --include="*.ts" | grep -E "(POST|PUT|DELETE|PATCH)"
grep -rn "axios\.(post|put|delete|patch)" --include="*.js" --include="*.ts"

Read the full file on GitHub · 135 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 135 lines · 89 tokens per session scan A 6ac4708d15b6

Subscribe to this mod's changes

frontend-security is a skill published in the GitHub repository schalkneethling/webdev-agent-skills (7 stars, last pushed 6mo ago), licensed MIT. It adds 89 tokens to every session and 1,606 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

frontend-security compared with skills from other repositories

frontend-security next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
frontend-securityschalkneethling/webdev-agent-skillsSkill76mo agoMITA89Claude Code, Codex
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code