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 skills add serejaris/kimi-skills --skill code-safety-auditgit clone --depth 1 https://github.com/serejaris/kimi-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/skills/serejaris/kimi-skills/code-safety-audit)<a href="https://agentmods.dev/skills/serejaris/kimi-skills/code-safety-audit"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/code-safety-audit/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/skills/serejaris/kimi-skills/code-safety-audit"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/code-safety-audit.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 | $0.00069 | $0.01491 |
| Opus 5 | $0.00034 | $0.00745 |
| Sonnet 5 | $0.00014 | $0.00298 |
| Haiku 4.5 | $0.00007 | $0.00149 |
Grade A, and why
code-safety-audit scanned grade A with 1 finding 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 10d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| A03: 注入 | SQL 注入、命令注入 (os.system/subprocess shell/eval/exec)、XSS (innerHTML/document.write/dangerouslySetInnerHTML/v-html) | How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
security-scanner
代码安全扫描工具，提供三大扫描能力：
- 依赖漏洞扫描 — 自动检测 npm / pip 依赖中的已知漏洞
- 密钥泄露检测 — 通过正则匹配 + Shannon 熵值分析发现硬编码的密钥、Token、密码
- OWASP 模式检测 — 识别 SQL 注入、XSS、命令注入、不安全反序列化等常见安全反模式
Quick Start
# 扫描当前目录（全部检查项）
python3 scripts/security_scan.py .
# 仅扫描依赖漏洞
python3 scripts/security_scan.py --mode deps .
# 仅检测密钥泄露
python3 scripts/security_scan.py --mode secrets /path/to/project
# 仅检测 OWASP 安全模式
python3 scripts/security_scan.py --mode owasp .
# 输出 JSON 格式报告
python3 scripts/security_scan.py --format json --output report.json .
# 只显示 high 及以上严重级别
python3 scripts/security_scan.py --severity high .
扫描模块详情
1. 依赖漏洞扫描 (deps)
自动检测项目类型并调用相应工具：
| 项目类型 | 检测文件 | 使用工具 |
|---|---|---|
| Node.js | package.json + package-lock.json |
npm audit |
| Python | requirements.txt / pyproject.toml / Pipfile |
pip-audit |
如果对应的审计工具未安装，会给出提示而不是报错。
2. 密钥泄露检测 (secrets)
通过两种方式检测：
正则匹配：覆盖常见的密钥格式
| 密钥类型 | 示例模式 |
|---|---|
| AWS Access Key | AKIA 开头的 20 字符 |
| GitHub Token | ghp_、github_pat_ 开头 |
| Slack Token | xoxb-、xoxp- 开头 |
| Stripe Key | sk_live_、pk_live_ 开头 |
| 私钥文件 | -----BEGIN PRIVATE KEY----- |
| 通用 API Key | api_key = "..." 格式 |
| URL 内嵌凭据 | https://user:pass@host |
| JWT Token | eyJ... 格式 |
Shannon 熵值分析：对代码中的字符串常量计算信息熵（阈值 > 4.5 且长度 >= 20），用于发现非标准格式的密钥。
3. OWASP 模式检测 (owasp)
覆盖 OWASP Top 10 中可静态检测的安全模式：
| OWASP 分类 | 检测模式 |
|---|---|
| A02: 密码学失败 | 弱哈希 (MD5/SHA1)、弱加密 (DES/RC4) |
| A03: 注入 | SQL 注入、命令注入 (os.system/subprocess shell/eval/exec)、XSS (innerHTML/document.write/dangerouslySetInnerHTML/v-html) |
| A04: 不安全设计 | 路径遍历 |
| A05: 安全配置错误 | Debug 模式开启、CORS 通配符、绑定 0.0.0.0 |
| A08: 完整性失败 | 不安全反序列化 (pickle/yaml.load/marshal/unserialize) |
| A10: SSRF | 用户输入直接用于 HTTP 请求 |
支持语言：Python、JavaScript/TypeScript、Java、PHP、Ruby、Go 等。
参数说明
| 参数 | 说明 | 默认值 |
|---|---|---|
TARGET |
扫描目标目录 | 当前目录 |
--mode MODE |
扫描模式：all、deps、secrets、owasp |
all |
--format FORMAT |
输出格式：text、json |
text |
--output FILE |
输出文件路径 | stdout |
--severity LEVEL |
最低报告级别：low、medium、high、critical |
low |
--exclude-dir DIR |
额外排除的目录（可重复使用） | - |
--max-file-kb SIZE |
单文件最大扫描大小 (KB) | 512 |
-h, --help |
显示帮助 | - |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 153 lines · 69 tokens per session scan A c24d228c25f0
code-safety-audit is a skill published in the GitHub repository serejaris/kimi-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 1,491 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
offensive-wifi
Wireless / 802.11 attack methodology for red team engagements and wireless security assessments. Covers monitor-mode setup, WPA/WPA2-PSK handshake capture and PMKID attacks, WPA3 SAE downgrade and Dragonblood, WPA-Enterprise (EAP) attacks (MSCHAPv2 cracking, EAP-TLS cert theft, evil-twin RADIUS), Karma / Known Beacons…
syndic
Gère un parc de copropriétés en France avec vue portfolio consolidée. Couvre administration, comptabilité (décret 2005, plan comptable copro, 5 annexes), assemblées générales (convocation, PV, notification), appels de fonds, travaux, fournisseurs, recouvrement d'impayés et transition de syndic. Maîtrise les majorités…
offensive-bluetooth-classic
Bluetooth Classic (BR/EDR) attack methodology — device discovery, service enumeration via SDP, LMP/L2CAP layer attacks, legacy PIN cracking (BlueBorne / KNOB), Bluetooth file-transfer abuse (BlueSnarfing legacy), unauthenticated profile abuse (HSP, HFP, OPP), and modern relevance against older industrial / automotive…
agent-wiki
Incremental LLM-friendly wiki generator for Obsidian note vaults. Use when: (1) Building wiki from notes, (2) Ingesting notes to wiki, (3) Obsidian LLM wiki, (4) Incremental knowledge base management. Triggers: 'build wiki from notes', 'ingest notes to wiki', 'Obsidian LLM wiki', 'incremental knowledge base'.
design-md-validator
Validate DESIGN.md files against the official Google specification using the @google/design.md CLI linter. Works with local files. Use when the user wants to lint a DESIGN.md, check spec compliance, find broken token references, verify WCAG contrast ratios, diff two versions, export tokens to Tailwind or DTCG format…
agent-ready-oauth-protected-resource
Sub-skill de agent-ready-cloudflare: Implement OAuth Protected Resource Metadata.