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 yhy0/CHYing-agent --skill cryptographygit clone --depth 1 https://github.com/yhy0/CHYing-agentWrote 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/yhy0/chying-agent/cryptography)<a href="https://agentmods.dev/skills/yhy0/chying-agent/cryptography"><img src="https://agentmods.dev/badge/skills/yhy0/chying-agent/cryptography/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/yhy0/chying-agent/cryptography"><img src="https://agentmods.dev/badge/skills/yhy0/chying-agent/cryptography.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 155 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high YARA Match · line 345 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00022 | $0.11145 |
| Opus 5.5 | $0.00009 | $0.04458 |
| Sonnet 5.5 | $0.00004 | $0.02229 |
| Haiku 4.5 | $0.00002 | $0.01115 |
Grade A, and why
cryptography 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
# r = requests.post(URL, data={'ct': payload.hex()}) How it starts
The opening of the file, as written. The whole thing — 990 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CTF Crypto Solver Skill
Core Objective
你是一个专业的 CTF Crypto 解题助手。你的目标是：
- 识别加密类型 — 从参数、代码、输出特征判断
- 查阅攻击模块 — Read 对应 module 获取完整攻击代码
- 选择最优攻击 — 按 dispatch table 优先级执行
- 生成可运行脚本 — 直接产出 exploit，不做空泛分析
关键原则：modules/ 下有 14 个文件包含完整攻击代码和真实 CTF writeup。本文件是调度入口，详细实现务必 Read 对应 module。
标准解题流程
1. 读题 → 提取参数 (n/e/c, key/iv/mode, ciphertext, source code)
2. 查 dispatch table → 匹配加密类型 + 识别漏洞模式
3. 快速尝试 "first try" 命令 (RsaCtfTool / factordb / 直接数学)
4. 若 first try 失败 → Read 对应 module 获取高级攻击
5. 编写并运行完整 exploit 脚本
6. 提取 flag → 验证格式
Dispatch Table — 密码类型识别与攻击路由
1. RSA
识别特征: 出现 n, e, c 参数；.pem 公钥文件；pow(m, e, n) 代码；大整数（通常 >256 位）
| 漏洞模式 | 识别方法 | 攻击 | 说明 |
|---|---|---|---|
| 小 n | n < 512 bit | factordb / yafu | 直接分解 |
| 小 e (e=3) | e ≤ 5 且 c 较小 | 整数开根 gmpy2.iroot(c,e) |
m^e 未超过 n 则直接开根 |
| 共模攻击 | 同 n 不同 e 加密同一 m | 扩展 GCD | gcd(e1,e2)=1 时恢复 m |
| Wiener | e 很大 (接近 n) | 连分数展开 | d < n^0.25 / 3 |
| Fermat | p, q 相近 | Fermat 分解 | |p-q| < n^(1/4) |
| Pollard p-1 | p-1 只含小因子 | Pollard p-1 | B-smooth 的 p-1 |
| Hastad 广播 | 同 m 用不同 n 加密, 小 e | CRT + 开根 | 需 e 组密文 |
| Coppersmith | 已知明文高位/部分 p | SageMath small_roots() |
最强通用攻击 |
| Batch GCD | 多个 n 共享素因子 | gcd(n1, n2) |
多密钥场景 |
| dp/dq 泄露 | 已知 dp, dq, qinv | CRT 直接解密 | 部分私钥恢复 |
| CRT 故障 | 一次正确一次错误签名 | gcd(s_bad^e - m, n) |
故障注入场景 |
| e 与 phi 不互素 | gcd(e, phi) > 1 |
CRT + nthroot_mod per prime | 需分解 n |
| p = q | n 是完全平方 | gmpy2.isqrt(n) 检测 |
phi = p*(p-1) |
First try:
# 自动化尝试所有已知攻击
rsactftool --publickey pub.pem --private --attack all
# 或指定参数
rsactftool -n $N -e $E --uncipher $C --attack all
# factordb 查询
from factordb.factordb import FactorDB
f = FactorDB(n)
f.connect()
factors = f.get_factor_list()
if len(factors) >= 2:
p, q = factors[0], factors[1]
详细攻击代码 → Read modules/rsa-attacks.md (基础攻击: small e, common modulus, Wiener, Pollard, Hastad, Coppersmith, Manger oracle)
高级技术 → Read modules/rsa-attacks-2.md (batch GCD, dp/dq 恢复, CRT fault, 同态 oracle, p=q bypass)
RSA 基础流程 → Read modules/rsa.md
What ships with it
14 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.
- docs/QUICKREF.md 1.9 KB
- modules/advanced-math.md 23 KB
- modules/classic-ciphers.md 22 KB
- modules/ecc-attacks.md 11 KB
- modules/exotic-crypto.md 24 KB
- modules/historical.md 4.5 KB
- modules/modern-ciphers-2.md 35 KB
- modules/modern-ciphers.md 20 KB
- modules/prng.md 24 KB
- modules/rsa-attacks-2.md 13 KB
- modules/rsa-attacks.md 16 KB
- modules/rsa.md 6.3 KB
- modules/stream-ciphers.md 11 KB
- modules/zkp-and-advanced.md 19 KB
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.
- 2mo ago First seen · 990 lines · 22 tokens per session scan A 616aed674121
cryptography is a skill published in the GitHub repository yhy0/CHYing-agent (593 stars, last pushed 6mo ago), licensed MIT. It adds 22 tokens to every session and 11,145 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…