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 skills/fb0sh/pentester/pentester-waf-bypassnpx skills add fb0sh/pentester --skill pentester-waf-bypassgit clone --depth 1 https://github.com/fb0sh/pentesterWrote 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/fb0sh/pentester/pentester-waf-bypass)<a href="https://agentmods.dev/skills/fb0sh/pentester/pentester-waf-bypass"><img src="https://agentmods.dev/badge/skills/fb0sh/pentester/pentester-waf-bypass.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 5.1 | $0.00064 | $0.01457 |
| Opus 5 | $0.00032 | $0.00728 |
| Sonnet 5 | $0.00013 | $0.00291 |
| Haiku 4.5 | $0.00006 | $0.00146 |
Grade A, and why
pentester-waf-bypass 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 6d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WAF 绕过与过滤器差异分析
本文用于 CTF、靶场、代码审计和明确授权的安全测试。测试时优先使用
SELECT 1、whoami、alert(1)等低影响验证载荷,避免破坏数据、写入后门或访问无关敏感信息。
1. 核心分析模型
多数 WAF 绕过源于以下差异:
- 解码次数差异 — WAF 与后端的解码次数不同
- 语法解析差异 — WAF 与解释器的语法解析规则不同
- 规范化差异 — WAF 检查原始请求,后端处理规范化后的请求
- 检查覆盖差异 — WAF 只检查部分参数、请求体或 Content-Type
- 匹配模式差异 — 黑名单匹配过于简单
- 重组可能性差异 — 过滤结果仍能重新组合成危险语句
分析任何过滤器时,按以下链路观察:
原始请求
↓
代理服务器解析
↓
URL / Unicode / HTML 实体解码
↓
WAF 规则匹配
↓
Web 框架参数解析
↓
应用程序二次处理
↓
数据库、Shell、模板引擎或浏览器解释
绕过测试的重点是确定:
- WAF 检查的是原始值还是解码后的值
- 请求会经历几次解码
- 大小写是否统一
- 注释和空白是否规范化
- 重复参数取第一个、最后一个还是全部
- 后端最终执行的字符串是什么
2. PHP WAF 绕过
preg_replace 双写绕过(关键技巧)
preg_replace() 会循环替换直到没有匹配为止,但如果关键词被替换后拼出了新的关键词,只会替换内层,外层保留。
核心原理:preg_replace('/NSSCTF/', '', 'NSSNSSCTFCTF') → 删除中间的 NSSCTF → 剩下 NSS + CTF = NSSCTF
通用模板:
假设过滤关键词为 X(如 NSSCTF)
构造输入: X拆成两半, 在中间嵌入完整X
即: X前半 + X + X后半
示例:
过滤 NSSCTF → 输入 NSS + NSSCTF + CTF = NSSNSSCTFCTF
过滤 flag → 输入 fl + flag + ag = flflagag
过滤 cat → 输入 ca + cat + t = cacatt
过滤 system → 输入 sys + system + tem = syssystemtem
为什么简单的大小写绕过不适用于 preg_replace:
preg_replace('/NSSCTF/', '', 'NssCTF')→Nss不匹配NSS(无 i 修饰符)→ 原样输出NssCTFNssCTF !== "NSSCTF"(严格比较失败)→ 不通过- 只有双写绕过才能让替换后恰好得到原始关键词字符串
识别场景:
- 源码含
preg_replace('/关键词/', '', $input)且需要$input替换后等于关键词本身 → 立即用双写绕过 - 不要尝试大小写绕过(替换后不等于原关键词)或编码绕过(编码字符串不等于原关键词)
函数名混淆
- Base64 编码恢复:
$f=base64_decode('c3lzdGVt');$f('id'); - 字符串拼接:
$f='sys'.'tem';$f('id'); - 可变函数:
$a='sys';$b='tem';$a$b('id');
关键字绕过
- 拆分路径:
'/va'.'r/ww'.'w/ht'.'ml' - 注释绕过:
sys/**/tem('id'); - 反转字符串:
$f=strrev('metsys');$f('id');
3. SQL 注入绕过
关键字绕过
- 大小写混合:
SeLeCt代替SELECT - 内联注释:
S/*!ELECT*/ - 双重编码:
%2565→%65→e - 等价函数:
GROUP_CONCAT替代concat_ws
注释符变体
-- -代替----+代替--#代替--
4. 命令注入绕过
分隔符变体
- 换行符:
id\nwhoami - 管道符:
id|whoami - 逻辑运算:
id&&whoami - 子 shell:
$(id)或`id`
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.
- 6d ago First seen · 147 lines · 64 tokens per session scan A de0a31b8345a
pentester-waf-bypass is a skill published in the GitHub repository fb0sh/pentester (23 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 1,457 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
transilience-report-style
Threat Intelligence Report Design System — ReportLab-based PDF generation for A4 reports with Transilience branding, typography, and layout standards.
firewall-review
Evidence-safe firewall ruleset audit reference specification — 22 documented detector patterns (17 vendor-agnostic plus 5 FortiGate-specific), a 15-check semantic catalogue, CIS Fortinet FortiGate Benchmark guidance, a custom customer-policy benchmark, and consolidated network-team Excel profiles including grouped…
pentest-engagement
Run a professional penetration engagement OR a network vulnerability scan from a scope. WEB mode (apex domains / app URLs) — mandatory surface expansion, systematic OWASP attack-class coverage, reversible active exploitation, authoritative validation, Transilience PDF. NETWORK mode (a list of IPs/CIDRs, e.g. 1500…
coordination
Pentest coordination — orchestrates executor and validator agents with context-controlled spawning. Entry point for all engagements.
hackerone
HackerOne bug bounty automation - parses scope CSVs, deploys parallel pentesting agents per asset, validates PoCs, and generates platform-ready submission reports.
pci-secure-software
Automated PCI Secure Software Standard (SSS) v2.0 readiness gap-assessment of an application from its source code and documentation. Deterministically enumerates every applicable Test Requirement from a pinned catalog, gathers source/doc evidence, and emits an evidence-bound per-requirement verdict (MET / NOTMET /…