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 nanxiaoyao/network-huawei-skills --skill attack-defensegit clone --depth 1 https://github.com/nanxiaoyao/network-huawei-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/nanxiaoyao/network-huawei-skills/attack-defense)<a href="https://agentmods.dev/skills/nanxiaoyao/network-huawei-skills/attack-defense"><img src="https://agentmods.dev/badge/skills/nanxiaoyao/network-huawei-skills/attack-defense/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/nanxiaoyao/network-huawei-skills/attack-defense"><img src="https://agentmods.dev/badge/skills/nanxiaoyao/network-huawei-skills/attack-defense.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 | $0.00113 | $0.01832 |
| Opus 5 | $0.00056 | $0.00916 |
| Sonnet 5 | $0.00023 | $0.00366 |
| Haiku 4.5 | $0.00011 | $0.00183 |
Grade A, and why
attack-defense 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 11d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
华为 USG 攻击防范配置技能 (attack-defense)
适用平台 USG6000E 系列 适用版本 V600R007C20+ 文档来源 HUAWEI USG6000E V600R007C20 产品文档 (案例 sec_case_defend_*)
USG 攻击防范分三层 单包攻击防范（畸形/扫描类）+ 流量型攻击防范（DDoS）+ 应用层攻击防范（HTTP/DNS Flood）
触发场景
- 公网链路被刷流量 怀疑 DDoS
- 服务器 syn-flood / udp-flood 攻击
- 应用层 HTTP-flood CC 攻击
- 配置源地址校验 防 IP 欺骗
- 限制单 IP 新建连接数 防爬虫/扫描
- 联动 IDS/HiSec Insight 做高级威胁防御
- 终端准入 SACG 联动
防护体系全景
┌───────────────────────────────────────────────────┐
│ 应用层 HTTP-Flood / DNS-Flood / SIP-Flood │
│ ├─ 指纹学习 dynamic-fingerprint-learn │
│ └─ 源认证 source-detect │
├───────────────────────────────────────────────────┤
│ 流量层 SYN/UDP/ICMP Flood + 动态限流 │
│ ├─ alert-rate 阈值告警 │
│ ├─ defend 启用清洗 │
│ └─ auto-defend 动态 CAR │
├───────────────────────────────────────────────────┤
│ 单包层 畸形包 IP/TCP options 扫描 │
│ └─ firewall defend XXX enable │
├───────────────────────────────────────────────────┤
│ 入口层 URPF 反向路径校验 防 IP 欺骗 │
└───────────────────────────────────────────────────┘
一 Anti-DDoS 防 DDoS
配置三步走
- 接口启用流量统计
anti-ddos flow-statistic enable - 启用基线学习 自适应阈值
anti-ddos baseline-learn start - 配置各攻击类型 alert/defend
经典模板 来自 sec_case_defend_0005
system-view
interface GigabitEthernet 0/0/1
anti-ddos flow-statistic enable
quit
anti-ddos syn-flood source-detect
anti-ddos syn-flood defend alert-rate 3000
anti-ddos udp-flood dynamic-fingerprint-learn alert-speed 80
anti-ddos udp-frag-flood dynamic-fingerprint-learn alert-speed 50
anti-ddos http-flood defend alert-rate 9000
anti-ddos http-flood source-detect mode basic
anti-ddos baseline-learn tolerance-value 100
anti-ddos baseline-learn start
阈值原则
- 业务峰值 ×3 作为 alert-rate
- 先观察 1-2 周 学习基线 再开 defend
- tolerance-value 100 表示允许超基线 100%
二 单包攻击防范
适用：畸形包 land smurf fraggle teardrop 端口扫描 IP-Sweep TCP options
firewall defend land enable
firewall defend smurf enable
firewall defend fraggle enable
firewall defend tcp-flag enable
firewall defend ip-fragment enable
firewall defend ip-spoofing enable
firewall defend route-record enable
firewall defend source-route enable
firewall defend ip-sweep enable
firewall defend ip-sweep max-rate 5000 blacklist-timeout 20
firewall defend port-scan enable
firewall defend port-scan max-rate 4000 blacklist-timeout 20
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.
- 11d ago First seen · 190 lines · 113 tokens per session scan A b9cfe7ba7ffa
attack-defense is a skill published in the GitHub repository nanxiaoyao/network-huawei-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 113 tokens to every session and 1,832 once invoked, about $0.0006 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 skills, from other repositories
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
seedance-vocab-zh
This skill should be used when the user asks for Chinese Seedance 2.0 prompt wording, Mandarin cinematic vocabulary, Chinese prompt compression, or translation of camera, lighting, action, VFX, audio, and production terms into Chinese.
percepxion-oob
Manage Lantronix out-of-band (OOB) infrastructure via Percepxion central management platform: device inventory, serial port inspection via SLC CLI, firmware compliance, config management, security auditing, and closed-loop incident remediation. Use during outages, maintenance windows, compliance cycles, and…
fmc-firewall-ops
Cisco Secure Firewall FMC — access policy search, rule inspection, FTD device targeting, multi-FMC profile management. Use when searching firewall rules by IP or FQDN, checking if host A can reach host B through the firewall, auditing FMC access policies, or reviewing SGT-based segmentation rules.
setup-matt-pocock-skills
A setup skill that configures engineering skills for a repository, including its issue tracker, labels, and documentation layout. A repository is the project folder managed by version control.