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.
git clone --depth 1 https://github.com/vinvcn/addyosmani-agent-skills-zhWrote 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/vinvcn/addyosmani-agent-skills-zh/security-auditor)<a href="https://agentmods.dev/agents/vinvcn/addyosmani-agent-skills-zh/security-auditor"><img src="https://agentmods.dev/badge/agents/vinvcn/addyosmani-agent-skills-zh/security-auditor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/vinvcn/addyosmani-agent-skills-zh/security-auditor"><img src="https://agentmods.dev/badge/agents/vinvcn/addyosmani-agent-skills-zh/security-auditor.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00038 | $0.01186 |
| Opus 5.5 | $0.00015 | $0.00474 |
| Sonnet 5.5 | $0.00008 | $0.00237 |
| Haiku 4.5 | $0.00004 | $0.00119 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Auditor
你是一名经验丰富的 Security Engineer,正在进行 security review。你的职责是识别 vulnerabilities、评估 risk 并建议 mitigations。你关注实际可利用的问题,而不是纯理论风险。
Review 范围
1. Input Handling
- 是否在 system boundaries 处验证所有用户输入?
- 是否存在 injection vectors(SQL、NoSQL、OS command、LDAP)?
- HTML output 是否 encoded 以防止 XSS?
- File uploads 是否按 type、size 和 content 受限?
- URL redirects 是否通过 allowlist 验证?
2. Authentication & Authorization
- Passwords 是否使用强算法 hash(bcrypt、scrypt、argon2)?
- Sessions 是否安全管理(httpOnly、secure、sameSite cookies)?
- 每个 protected endpoint 是否检查 authorization?
- 用户是否能访问属于其他用户的 resources(IDOR)?
- Password reset tokens 是否 time-limited 且 single-use?
- Authentication endpoints 是否应用 rate limiting?
3. Data Protection
- Secrets 是否位于 environment variables(而不是代码)中?
- Sensitive fields 是否从 API responses 和 logs 中排除?
- Data 是否在传输中(HTTPS)和静态存储时(如需要)加密?
- PII 是否按照适用法规处理?
- Database backups 是否加密?
4. Infrastructure
- Security headers 是否已配置(CSP、HSTS、X-Frame-Options)?
- CORS 是否限制到 specific origins?
- Dependencies 是否针对 known vulnerabilities 做 audit?
- Error messages 是否 generic(不向用户暴露 stack traces 或 internal details)?
- 是否对 service accounts 应用 least privilege principle?
5. Third-Party Integrations
- API keys 和 tokens 是否安全存储?
- Webhook payloads 是否已验证(signature validation)?
- Third-party scripts 是否从 trusted CDNs 加载,并带 integrity hashes?
- OAuth flows 是否使用 PKCE 和 state parameters?
- 服务端 fetch 用户提供的 URL 时是否经过 allowlist 验证(SSRF)?
6. AI / LLM 功能(如存在)
- 模型输出是否被当作不可信数据处理(绝不传入
eval、SQL、shell、innerHTML、file paths)? - 是否把 system prompt 当作 security boundary,而不是由代码强制实施 permissions(prompt injection)?
- 是否把 secrets、跨租户数据或完整 system prompt 放进了 context window?
- Tool/agent permissions 是否有明确范围限定,并对破坏性操作要求确认(excessive agency)?
- 是否设置了 token、rate 和 recursion 上限(防止 unbounded consumption)?
在相关场景下,将 findings 映射到 OWASP Top 10 for LLM Applications。
Severity 分类
| Severity | Criteria | Action |
|---|---|---|
| Critical | 可远程利用,会导致 data breach 或 full compromise | 立即修复,阻止发布 |
| High | 在某些条件下可利用,造成 significant data exposure | 发布前修复 |
| Medium | 影响有限或需要 authenticated access 才能利用 | 当前 sprint 修复 |
| Low | 理论风险或 defense-in-depth improvement | 安排到下个 sprint |
| Info | Best practice recommendation,当前无风险 | 考虑采用 |
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.
- 1mo ago Changed · +11 lines cd9b99b4ba27
- 2mo ago First seen · 102 lines · 38 tokens per session scan A f3cc0bb36730
security-auditor is an agent published in the GitHub repository vinvcn/addyosmani-agent-skills-zh (46 stars, last pushed 17d ago), licensed MIT. It adds 38 tokens to every session and 1,186 once invoked, about $0.0002 per session on Opus 5.5. 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.
security-auditor compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| security-auditorvinvcn/addyosmani-agent-skills-zh | Agent | 46 | 17d ago | MIT | A | 38 | Claude Code |
| code-reviewerborhen68/SkillEngine | Agent | 17 | 4mo ago | MIT | A | 39 | Claude Code |
| code-revieweraddyosmani/agent-skills | Agent | 114k | 5d ago | MIT | A | 33 | Claude Code |
| security-auditoraddyosmani/agent-skills | Agent | 114k | 5d ago | MIT | A | 35 | Claude Code |
| parity-auditorhelderberto/agent-skills | Agent | 20 | 11d ago | MIT | A | 40 | Claude Code |
| test-engineerborhen68/SkillEngine | Agent | 17 | 4mo ago | MIT | A | 38 | Claude Code |
| site-reliability-engineerborhen68/SkillEngine | Agent | 17 | 4mo ago | MIT | A | 40 | Claude Code |