Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计通过

owasp-security-reviewowasp 安全审查

Agent Skill

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。它适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据或生产系统时,应先确认最小权限、脱敏方式和操作边界。

总安装

964

周安装

41

GitHub Stars

14

下载量

338
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:owasp-security-review(owasp 安全审查)
来源仓库:https://github.com/jgamaraalv/ts-dev-kit
仓库路径:skills/owasp-security-review
安装命令:
npx skills add https://github.com/jgamaraalv/ts-dev-kit --skill owasp-security-review
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/jgamaraalv/ts-dev-kit --skill owasp-security-review

简介

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。

  • 它适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。
  • 通过 npx skills add 命令从指定仓库安装,需结合原始 README 核验具体用法。
  • 使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据时应先确认最小权限。
  • owasp-security-review 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

OWASP Top 10:2025 Security Review

<quick_reference>

Quick reference

#CategoryKey riskAvg incidence
A01Broken Access ControlUnauthorized data access, privilege escalation, SSRF, CSRF3.74%
A02Security MisconfigurationDefault creds, verbose errors, missing hardening, XXE3.00%
A03Software Supply Chain FailuresVulnerable/malicious dependencies, compromised build pipelines5.72%
A04Cryptographic FailuresWeak algorithms, hardcoded keys, missing encryption, weak hashing3.80%
A05InjectionSQLi, XSS, command injection, LDAP/XPath/EL injection3.08%
A06Insecure DesignMissing threat modeling, business logic flaws, insufficient controls1.86%
A07Authentication FailuresCredential stuffing, weak passwords, session fixation, missing MFA2.92%
A08Software/Data Integrity FailuresUnsigned updates, insecure deserialization, untrusted CDN code2.75%
A09Security Logging & Alerting FailuresMissing audit logs, no alerting, log injection, sensitive data in logs3.91%
A10Mishandling of Exceptional ConditionsFailing open, info leakage via errors, unchecked return values2.95%

Severity classification

Use these severity levels when reporting findings:

  • Critical: Directly exploitable, leads to full system compromise or mass data breach (e.g., SQLi with no parameterization, hardcoded admin credentials, missing auth on admin endpoints).
  • High: Exploitable with moderate effort, significant data exposure or privilege escalation (e.g., IDOR, weak password hashing, SSRF, deserialization of untrusted data).
  • Medium: Exploitable under specific conditions, limited impact (e.g., missing CSRF protection, verbose error messages, missing security headers).
  • Low: Defense-in-depth issue, minimal direct impact (e.g., missing rate limiting, incomplete logging, suboptimal crypto configuration).

</quick_reference>

Workflows

<phase_1_code_review>

Code review for security

Systematically check the code against each relevant category:

  1. Identify the code's surface area — Does it handle auth? User input? File uploads? External data? Crypto? Error responses?
  2. Select relevant categories from the table above based on the surface area.
  3. Load the reference file for each relevant category and check the code against the "What to look for" section.
  4. Report findings grouped by category with severity (Critical/High/Medium/Low), the specific code location, and a concrete fix.

Priority order for review (highest impact first):

  • [CRITICAL] Input handling code → A05 (Injection), A01 (Access Control)
  • [CRITICAL] Auth/session code → A07 (Authentication), A01 (Access Control)
  • [HIGH] Data storage/transmission → A04 (Cryptographic Failures)
  • [HIGH] Configuration/deployment → A02 (Security Misconfiguration)
  • [HIGH] Dependencies → A03 (Supply Chain)
  • [MEDIUM] Error handling → A10 (Exceptional Conditions), A09 (Logging)
  • [MEDIUM] Architecture/design → A06 (Insecure Design)
  • [MEDIUM] Data integrity → A08 (Integrity Failures) </phase_1_code_review>

<phase_2_audit_checklist>

Security audit checklist

Generate a checklist for a feature or codebase:

  1. Read the feature/codebase to understand its scope.
  2. For each of the 10 categories, determine if it applies.
  3. For applicable categories, load the reference file and produce a checklist of items to verify.
  4. Output a markdown checklist grouped by category. </phase_2_audit_checklist>

<phase_3_remediation>

Remediation guidance

When a vulnerability is identified:

  1. Classify it into the correct OWASP category.
  2. Load the corresponding reference file.
  3. Apply the prevention checklist to produce a specific, actionable fix.
  4. Provide a code example of the fix when possible. </phase_3_remediation>

Reference files

Load the relevant file when you need detailed guidance for a specific category:

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

37.44%
按下载量换算127

Claude

30.73%
按下载量换算104

Cursor

20.03%
按下载量换算68

Gemini CLI

9.35%
按下载量换算32

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills