security-scan

security-scan is a skill for Claude Code from kazdenc/builder-skills. It costs 67 tokens per session (1,850 once invoked), scanned A, original, MIT.

A security review based on the OWASP Top 10, a widely used list of common web application security risks.

In plain words
What is it for?
Use it to scan code, rate security findings by severity, point to affected files and lines, and suggest fixes.
Why use it?
It helps expose issues such as injection, cross-site scripting, authentication mistakes, and leaked secrets before the application ships.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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.

agentmods
npx agentmods add skills/kazdenc/builder-skills/security-scan
Any agent
npx skills add kazdenc/builder-skills --skill security-scan
Clone the repo
git clone --depth 1 https://github.com/kazdenc/builder-skills

Made for: Claude Code.

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 security-scan

README.md
[![agentmods](https://agentmods.dev/badge/skills/kazdenc/builder-skills/security-scan.svg)](https://agentmods.dev/skills/kazdenc/builder-skills/security-scan)
Your own site
<a href="https://agentmods.dev/skills/kazdenc/builder-skills/security-scan"><img src="https://agentmods.dev/badge/skills/kazdenc/builder-skills/security-scan.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,850 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00067 $0.01850
Opus 5 $0.00034 $0.00925
Sonnet 5 $0.00013 $0.00370
Haiku 4.5 $0.00007 $0.00185

Measured 6d ago against content hash 23613864f2eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

security-scan 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 6d 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.

.claude/skills/dev/review/security-scan/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scan code for OWASP Top 10 vulnerabilities. Report severity-rated findings with file:line references and fix recommendations. Flag what matters; skip what doesn't apply.

Scan Categories

Work through each OWASP category. For each, search for the specific code patterns listed.

1. Injection (A03:2021)

Pattern to find Risk What to verify
String concatenation in SQL queries SQL injection Use parameterized queries / prepared statements
Template literals in database calls NoSQL injection Use query builders or ORM methods with bound parameters
exec(), spawn(), system() with user input Command injection Validate/whitelist input, avoid shell execution
User input in LDAP filters LDAP injection Escape special characters, use parameterized filters
User input in regex constructors ReDoS Validate regex complexity, use re2 or set timeouts
eval(), Function(), vm.runInContext() Code injection Remove entirely; never evaluate user-controlled strings

2. Broken Authentication (A07:2021)

Pattern to find Risk What to verify
Plain-text password storage Credential theft Use bcrypt/scrypt/argon2 with proper work factor
Missing rate limiting on login endpoints Brute force Implement rate limiting and account lockout
Session tokens in URLs or localStorage Session hijack Use httpOnly secure cookies
JWT without expiration or with weak signing Token forgery Set short exp, use RS256 or ES256, rotate keys
Missing MFA on sensitive operations Account takeover Require step-up auth for destructive actions
Hardcoded credentials or default passwords Unauthorized access Use environment variables and secrets management

3. Sensitive Data Exposure (A02:2021)

Pattern to find Risk What to verify
API keys, tokens, passwords in source Credential leak Move to environment variables / secrets manager
Secrets in log output Log exfiltration Redact sensitive fields before logging
Missing TLS / HTTP used for sensitive data Man-in-the-middle Enforce HTTPS, use HSTS header
PII in error responses Information disclosure Return generic errors to clients, log details server-side
Sensitive data in client-side state Browser exposure Keep secrets server-side, minimize client-side PII
Missing encryption at rest Data breach Encrypt sensitive database columns and file storage

Read the full file on GitHub · 150 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. 6d ago First seen · 150 lines · 67 tokens per session scan A 23613864f2eb

Subscribe to this mod's changes

security-scan is a skill published in the GitHub repository kazdenc/builder-skills (44 stars, last pushed 6mo ago), licensed MIT. It adds 67 tokens to every session and 1,850 once invoked, about $0.0003 per session on Opus 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 2026-08-30.