security-scan

A codebase security audit that looks for common vulnerabilities, such as exposed passwords, unsafe database queries, cross-site scripting, and command injection.

In plain words
What is it for?
Use it to scan source code for hardcoded secrets and risky ways of handling user input, database queries, web content, and shell commands.
Why use it?
It helps find security problems before attackers or users encounter them. Uncertain patterns are flagged for review instead of being assumed safe.

Skill for Claude CodeCodex

Part of the claude-code-optimizer plugin — 25 skills, 4 hooks shipped together

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/huzaifa525/claude-code-optimizer/security-scan
Any agent
npx skills add huzaifa525/claude-code-optimizer --skill security-scan
Clone the repo
git clone --depth 1 https://github.com/huzaifa525/claude-code-optimizer

Made for: Claude Code, Codex.

Or install claude-code-optimizer, the plugin that ships this one along with the rest of its 25 skills, 4 hooks.

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,165 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 $0.00023 $0.01165
Opus 5 $0.00012 $0.00583
Sonnet 5 $0.00005 $0.00233
Haiku 4.5 $0.00002 $0.00117

Measured 3d ago against content hash 5c94f16c93f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

templates/.claude/skills/security-scan/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run a comprehensive security scan on the codebase.

Iron Law

No "probably safe." Verify or flag. If you cannot confirm a pattern is secure, flag it. False positives are cheap. Missed vulnerabilities are not.

Scan Checklist

1. Hardcoded Secrets (CRITICAL)

grep -rn "password\s*=\|api_key\s*=\|secret\s*=\|token\s*=" src/
grep -rn "BEGIN.*PRIVATE KEY" .
grep -rn "sk-\|pk_\|ghp_\|gho_\|AKIA" src/

Also check for:

  • Base64-encoded secrets (long random strings in config)
  • Secrets in comments ("// old password was...")
  • Secrets in test fixtures that match production patterns

2. SQL Injection

  • String concatenation in SQL queries ("SELECT * FROM " + table)
  • Raw queries without parameterization
  • ORM bypass with raw SQL
  • Dynamic table/column names from user input

3. XSS (Cross-Site Scripting)

  • dangerouslySetInnerHTML, innerHTML, document.write
  • Template rendering with unescaped user input ({!! !!}, | safe, <%- %>)
  • URL parameters reflected in page without encoding
  • SVG/image uploads that could contain scripts

4. Command Injection

  • exec(), spawn(), system() with user-controlled input
  • Template strings in shell commands
  • Unsanitized filenames in file operations

5. Authentication & Authorization

  • Routes/endpoints missing auth middleware
  • Role checks that can be bypassed (client-side only)
  • Password hashing (must be bcrypt/argon2/scrypt — NOT md5/sha1/sha256)
  • JWT: check expiry validation, algorithm confusion, secret strength
  • Session fixation or missing session regeneration on login

6. Input Validation

  • API endpoints accepting unvalidated input
  • Missing type checks, length limits, format validation
  • File upload: missing type restrictions, size limits, path traversal
  • Regex DoS (ReDoS) — catastrophic backtracking patterns

7. Sensitive Data Exposure

  • Sensitive data in logs (passwords, tokens, PII)
  • Stack traces or internal paths in error responses
  • .env files not in .gitignore
  • Sensitive data in URL query parameters (logged by proxies)
  • Missing HTTPS enforcement

Read the full file on GitHub · 133 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. 3d ago First seen · 133 lines · 23 tokens per session scan A 5c94f16c93f8

Subscribe to this mod's changes

security-scan is a skill published in the GitHub repository huzaifa525/claude-code-optimizer (9 stars, last pushed 5mo ago), licensed MIT. It adds 23 tokens to every session and 1,165 once invoked, about $0.0001 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 2026-08-31.