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 Prohao42/aimy-skill --skill aimy-src-huntgit clone --depth 1 https://github.com/Prohao42/aimy-skillWrote 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/prohao42/aimy-skill/aimy-src-hunt)<a href="https://agentmods.dev/skills/prohao42/aimy-skill/aimy-src-hunt"><img src="https://agentmods.dev/badge/skills/prohao42/aimy-skill/aimy-src-hunt/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/prohao42/aimy-skill/aimy-src-hunt"><img src="https://agentmods.dev/badge/skills/prohao42/aimy-skill/aimy-src-hunt.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 | $0.00066 | $0.01394 |
| Opus 5.5 | $0.00026 | $0.00558 |
| Sonnet 5.5 | $0.00013 | $0.00279 |
| Haiku 4.5 | $0.00007 | $0.00139 |
Grade A, and why
aimy-src-hunt 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: aimy-skill SRC 挖洞全流程
定位：aimy-skill 是验证判定层——人工定向找到可疑点后，由它快速确认、取证据、出报告。 SRC 的洞不是全站乱扫出来的，是"定向找点 + 工具验证"挖出来的。
0. RELATED ROUTING
- 具体漏洞打法加载对应知识技能：
sqli-sql-injection、idor-broken-object-authorization、xss-cross-site-scripting、ssrf-server-side-request-forgery、ssti-server-side-template-injection等 - 项目在工作目录中时：命令全量参考
docs/tool_guide.md，漏洞打法docs/vuln_playbooks.md， 报告写作docs/report_writing.md
1. 六步工作流
① 信息收集
python main.py recon https://target.com --deep
python main.py portscan target.com --ports 80,443,8080
python main.py dirfuzz https://target.com --max 200
python main.py waf https://target.com # 先判断有没有 WAF
技术栈决定打法权重：
- PHP + MySQL（老站）→ SQLi、文件包含、上传
- Java + Spring → SpEL / 反序列化 / 越权
- Node + Express → NoSQLi / 原型链污染
- Go → 注入少，重点在逻辑漏洞
② 攻击面梳理
python main.py crawl https://target.com --depth 2 --max-pages 100
python main.py param-mine https://target.com
python main.py graphql https://target.com/api/graphql # GraphQL 在 SRC 中高频
高价值功能点：登录/注册（逻辑绕过）、密码重置（token 可预测）、文件上传、 订单与支付（价格篡改）、API 越权（IDOR / BOLA）、OAuth 与 SSO 回调、导出与下载。
③ 认证登录（多数功能在登录后）
python main.py login --auth-url https://target.com/login --auth-type form \
--auth-user ACCOUNT --auth-pass PASS --session-file sess.json
之后所有检测命令都追加 --session-file sess.json 以保持登录态。
④ 定向检测（按可疑点选命令）
| 发现的可疑点 | 命令 |
|---|---|
| 数字 id 参数 | sqlcheck "URL" --session-file sess.json |
| 注入确认与利用 | sqli-weaponize "URL" --session-file sess.json |
| 输出或回显点 | xsscheck "URL" --session-file sess.json |
| XSS 防误报复核 | xss-validate "URL" --session-file sess.json |
| 命令执行点（ping 等） | cmdi "URL" |
| 模板渲染点 | ssti "URL" |
| 文件下载与路径参数 | lfi "URL" |
| 双账号越权对比 | idor "URL" --my-id 1001 --other-id 1002 --session-file a.json --session-file-b b.json |
| 请求走私 | smuggler URL --exploit |
| 云凭证泄露 | cloud-pwn --raw "AKIA..." |
| 反序列化 / JWT / CRLF | deser / jwt / crlf |
⑤ 验证利用
- 工具链自带负对照与误报过滤（
xss-validate、二阶验证、false_positive_filter）， 但出报告前必须人工复测一次 - 越权成立标准：用 A 的 cookie 访问 B 的资源，返回的是 B 的私有数据（而非通用占位页）
- SQLi 以
version()/database()回显作为验证完成标准，用最小证据链证明即可
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 · 97 lines · 66 tokens per session scan A 647e81dfa57e
aimy-src-hunt is a skill published in the GitHub repository Prohao42/aimy-skill (359 stars, last pushed 4d ago), licensed MIT. It adds 66 tokens to every session and 1,394 once invoked, about $0.0003 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 2026-10-12.
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…