Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Security Review · xu-xiang | DecimalAI

securityby xu-xiang

Security Review

xu-xiang/security-review

Source xu-xiang/everything-claude-code-zh ↗License MIT

在添加身份验证、处理用户输入、操作机密信息、创建 API 接口或实现支付/敏感功能时使用此技能。提供全面的安全自查清单和模式。

SkillScore95Maintained

Automatic

Security & AppSec pack

Last verified 8/12/2026

What it changes

Passed 21 of 22 test cases with the skill, and 19 of 22 without it.

Without skill86%

With skill95%

Checks it passed that the model alone missed

Sets SameSite attribute to Strict
Throws an error if the required environment variable is undefined or missing

2 fixed19 passed either way1 still failing0 broke

Pass-rate lift: +9 pp
Tokens: +152%
Agent turns: 0%
Response time: -11%

Model gemini-3.6-flashMeasured 8/12/2026v521 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/xu-xiang-security-review/SKILL.md https://app.decimal.ai/s/xu-xiang-security-review/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add xu-xiang-security-review, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/xu-xiang-security-review/ and pins it in .decimal/skills.lock

decimalai skills add xu-xiang-security-review

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/xu-xiang-security-review/SKILL.md https://app.decimal.ai/s/xu-xiang-security-review/SKILL.md

Raw file: /s/xu-xiang-security-review/SKILL.md ↗ · machine-readable summary at /s/xu-xiang-security-review.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 2

Prompt

When setting session cookies in web HTTP responses to mitigate cross-site request forgery, what exact SameSite cookie attribute value should be specified?

What was checked, without and with the skill
Checked	Without skill	With skill
Sets SameSite attribute to Strict	Missed	Passed

case-18 · gemini-3.6-flash · 8/12/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md489 linessingle file

安全性審查技能

此技能確保所有程式碼遵循安全性最佳實務並識別潛在漏洞。

何時啟用

實作認證或授權
處理使用者輸入或檔案上傳
建立新的 API 端點
處理密鑰或憑證
實作支付功能
儲存或傳輸敏感資料
整合第三方 API

安全性檢查清單

1. 密鑰管理

❌ 絕不這樣做

const apiKey = "sk-proj-xxxxx"  // 寫死的密鑰
const dbPassword = "password123" // 在原始碼中

✅ 總是這樣做

const apiKey = process.env.OPENAI_API_KEY
const dbUrl = process.env.DATABASE_URL

// 驗證密鑰存在
if (!apiKey) {
  throw new Error('OPENAI_API_KEY not configured')
}

驗證步驟

無寫死的 API 金鑰、Token 或密碼
所有密鑰在環境變數中
.env.local 在 .gitignore 中
git 歷史中無密鑰

Track record

Benchmark

21 / 22

test cases passed, vs 19 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

xu-xiang / everything-claude-code-zh

skills/security-review/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v5

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.