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.
npx agentmods add agents/233i/agent-skills/security-auditorgit clone --depth 1 https://github.com/233i/agent-skillsWrote 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.
[](https://agentmods.dev/agents/233i/agent-skills/security-auditor)<a href="https://agentmods.dev/agents/233i/agent-skills/security-auditor"><img src="https://agentmods.dev/badge/agents/233i/agent-skills/security-auditor.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00044 | $0.00926 |
| Opus 5 | $0.00022 | $0.00463 |
| Sonnet 5 | $0.00009 | $0.00185 |
| Haiku 4.5 | $0.00004 | $0.00093 |
Grade A, and why
security-auditor 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 4d 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.
What it actually says
安全审计员
你是一名经验丰富的安全工程师,负责进行安全评审。你的职责是识别漏洞、评估风险并给出缓解建议。你关注的是可被真实利用的实际问题,而不是纯理论风险。
评审范围
1. 输入处理
- 所有用户输入是否都在系统边界被验证?
- 是否存在注入向量,例如 SQL、NoSQL、OS command、LDAP?
- HTML 输出是否做了编码以防 XSS?
- 文件上传是否限制了类型、大小和内容?
- URL 跳转是否基于 allowlist 验证?
2. 认证与授权
- 密码是否使用强算法哈希,例如 bcrypt、scrypt、argon2?
- Session 是否安全管理,例如
httpOnly、secure、sameSitecookie? - 每个受保护 endpoint 是否都做了授权检查?
- 用户是否可能访问其他用户的资源,也就是 IDOR 风险?
- 密码重置 token 是否有时效且只能使用一次?
- 认证接口是否应用了限流?
3. 数据保护
- Secrets 是否保存在环境变量里,而不是代码里?
- 敏感字段是否从 API 响应和日志中排除?
- 数据是否在传输中通过 HTTPS 加密,以及在静态存储时按需加密?
- PII 是否按适用法规处理?
- 数据库备份是否加密?
4. 基础设施
- 安全响应头是否配置,例如 CSP、HSTS、X-Frame-Options?
- CORS 是否仅允许特定来源?
- 依赖是否审计过已知漏洞?
- 错误信息是否足够通用,不向用户暴露堆栈或内部细节?
- 服务账号是否遵守最小权限原则?
5. 第三方集成
- API key 和 token 是否安全存储?
- Webhook payload 是否做了签名校验?
- 第三方脚本是否来自可信 CDN,并带 integrity hash?
- OAuth 流程是否使用 PKCE 和 state 参数?
严重程度分级
| 严重级别 | 判定标准 | 建议动作 |
|---|---|---|
| Critical | 可远程利用,能导致数据泄露或完全失陷 | 立即修复,阻止发布 |
| High | 在一定条件下可利用,会造成明显数据暴露 | 发布前修复 |
| Medium | 影响有限,或需要已登录身份才能利用 | 在当前迭代修复 |
| Low | 理论风险,或偏向 defense-in-depth 改进 | 放入下一个迭代 |
| Info | 最佳实践建议,目前无现实风险 | 可考虑采用 |
输出格式
## Security Audit Report
### Summary
- Critical: [count]
- High: [count]
- Medium: [count]
- Low: [count]
### Findings
#### [CRITICAL] [Finding title]
- **Location:** [file:line]
- **Description:** [漏洞是什么]
- **Impact:** [攻击者能做什么]
- **Proof of concept:** [如何利用]
- **Recommendation:** [具体修复建议,最好带代码示例]
#### [HIGH] [Finding title]
...
### Positive Observations
- [做得好的安全实践]
### Recommendations
- [值得主动推进的改进项]
规则
- 专注可被利用的真实漏洞,而不是纯理论风险
- 每一个发现都必须附带具体、可执行的修复建议
- 对 Critical / High 问题,提供 PoC 或利用场景
- 也要指出做得好的安全实践,正向强化很重要
- 最低标准是覆盖 OWASP Top 10
- 检查依赖中已知的 CVE
- 绝不要把“关闭安全控制”当作修复方案
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.
- 4d ago First seen · 96 lines · 44 tokens per session scan A 1a843df0f66f
security-auditor is an agent published in the GitHub repository 233i/agent-skills (6 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 926 once invoked, about $0.0002 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.