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 commands/awarexone/agentic-bug-hunter/crlfgit clone --depth 1 https://github.com/Awarexone/Agentic-Bug-HunterWhat 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 | $0.00000 | $0.00506 |
| Opus 5 | $0.00000 | $0.00253 |
| Sonnet 5 | $0.00000 | $0.00101 |
| Haiku 4.5 | $0.00000 | $0.00051 |
Grade A, and why
crlf 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 2d 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.
Python's `urllib` refuses raw `\r\n` in a URL (it protects you), so the What it actually says
/crlf
Inject carriage-return/line-feed sequences into the path/query (and optionally the Host/forwarding headers) and check whether an attacker-controlled header lands in the response — proof of CRLF injection.
Usage
/crlf "https://target.com/redirect?url=x"
/crlf https://target.com/ --host-header
/crlf -l recon/target.com/urls/params.txt --json
Run directly:
tools/crlf_scanner.py "https://target.com/r?u=x" --host-header
What it injects
| Vector | Payloads |
|---|---|
| Encoded CRLF | %0d%0a, %0a, %0d, %250d%250a (double-encoded) |
| Header fold | %0d%0a%20Set-Cookie:... |
| UTF-8 bypass | %E5%98%8A%E5%98%8D (overlong CR/LF that defeats naive \r\n filters) |
| IIS unicode | %u000d%u000a |
| Host-header | Host: evil, X-Forwarded-Host, Forwarded: host=, CRLF-in-Host |
Detection canary: the payloads try to inject Set-Cookie: crlftest=1. If that
header appears in the response, it's confirmed.
Impact
- Set-Cookie injection → session fixation.
- Injected
Location→ open redirect / OAuth token theft. - Injected body → reflected XSS that survives CSP host allowlists.
- Host-header injection → password-reset poisoning (attacker host in reset link), cache poisoning.
Note
Python's urllib refuses raw \r\n in a URL (it protects you), so the
encoded variants are what actually go on the wire — that's intended. The
host-header path also flags when your attacker host is reflected in a Location
response header (reset-poisoning signal) even without a full CRLF.
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.
- 2d ago First seen · 51 lines · 0 tokens per session scan A 7f984f53b634
crlf is a command published in the GitHub repository Awarexone/Agentic-Bug-Hunter (4,651 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 506 tokens. 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 commands, from other repositories
recon
Run full recon pipeline on a target — subdomain enum (Chaos API + subfinder), live host discovery (dnsx + httpx), URL crawl (katana + waybackurls + gau), gf pattern classification, nuclei scan. Outputs to recon/ / directory. Usage: /recon target.com.
hunt
Active vulnerability hunting. Two-track dispatcher — asks Red Team vs WAPT, hands off to hunt-dispatch skill and sibling commands. Usage: /hunt target.com | /hunt .target.com | /hunt targets.txt [--vuln-class X] [--source-code P] [--chrome].
token-scan
Meme coin and token security scan — checks for rug pull vectors (hidden mint, honeypot, fee manipulation, LP lock bypass, authority retention, bonding curve exploits, fake renounce, sandwich amplification). Manual 8-class grep audit (with an optional automated scanner if present). Usage: /token-scan [--chain solana].
autopilot
Run autonomous hunt loop on a target — scope check → recon → rank surface → hunt → validate → report with configurable checkpoints. Usage: /autopilot target.com [--paranoid|--normal|--yolo].
triage
Quick 7-Question Gate triage on a finding before writing a report. Kills N/A submissions before they happen. Faster than /validate — for quick go/no-go decisions. Usage: /triage.
validate
Validate a finding — runs 7-Question Gate + 4-gate checklist. Kills weak findings before report writing. Prevents N/A submissions that hurt validity ratio. Usage: /validate.