Hunt HTTP Smuggling

What it does

When your agent uses it

• Hunting H1 paid programs running CDN+origin stacks
• Targeting load balancer / WAF bypass

Example prompts

• “/hunt-http-smuggling”

Requirements

• Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit a04bb83. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • curl

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Hunt HTTP Smuggling loads about 1.8k tokens when it runs. Until then it costs about 250 tokens; SKILL.md has 711 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~250

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from elementalsouls/Claude-BugHunter at commit a04bb83, republished under its MIT licence (© elementalsouls). 711 words, ~1,837 tokens.

name

hunt-http-smuggling

description

Hunt HTTP request smuggling (CL.TE, TE.CL, H2.CL, H2.TE). Cause: front-end proxy and back-end server disagree on where one request ends and the next begins (Content-Length vs Transfer-Encoding header parsing inconsistency). CL.TE: front-end uses CL, back uses TE → smuggle by sending TE: chunked but with body that fits CL count. TE.CL: opposite. H2.CL: HTTP/2 downgrade, smuggle CL into HTTP/1.1 back-end. Detection tools: Burp HTTP Request Smuggler extension, smuggler.py, h2csmuggler. Confirm: time-delay technique (smuggled GET with 30s timeout) — if front-end returns slow on next victim request, smuggling works. Validate: cache poisoning chain (smuggle request that gets cached for victim), credential theft (smuggle X-Forwarded-For override that captures next user's cookies), bypass auth (smuggled internal-path request). Real paid examples from major CDN deployments. Use when hunting H1 paid programs running CDN+origin stacks, when targeting load balancer / WAF bypass.

sources

hackerone_public, cve_database, portswigger_research, public_research

report_count

12

POST / HTTP/1.1
Content-Length: 13
Transfer-Encoding: chunked

0

SMUGGLED

1. Burp extension: HTTP Request Smuggler
2. Right-click request → Extensions → HTTP Request Smuggler → Smuggle probe
3. Manual timing: CL.TE probe + ~10s delay = backend waiting for rest of body

Poison next request → access admin as victim
Steal credentials → capture victim's session
Cache poisoning → stored XSS at scale

curl -sI https://target/ | grep -i "Server:"

© elementalsouls, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/hunt-http-smuggling of elementalsouls/Claude-BugHunter.

Open the folder on GitHubat commit a04bb83