arsenal
Show which external bug-bounty tools are installed on this machine and print install hints for the missing ones. Curated from high-signal repos. Use to…
Capture reproducible PoC evidence for a finding — raw request/response, copy-paste curl, HAR, optional screenshot, and a report-ready evidence.md. Secrets redacted by default. Usage: /poc capture <url> [-H ...] | /poc from-request req.txt [--response resp.txt]
$ npx -y skills add shuvonsec/claude-bug-bounty --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
/pocContext preview
What this command does when you run it.
Capture reproducible PoC evidence for a finding — raw request/response, copy-paste curl, HAR, optional screenshot, and a report-ready evidence.md. Secrets redacted by default. Usage: /poc capture <url> [-H ...] | /poc from-request req.txt [--response resp.txt]
description: Capture reproducible PoC evidence for a finding — raw request/response, copy-paste curl, HAR, optional screenshot, and a report-ready evidence.md. Secrets redacted by default. Usage: /poc capture <url> [-H ...] | /poc from-request req.txt [--response resp.txt]
Turn a finding into a **reproducible evidence bundle** — the exact request, the exact response, a copy-paste `curl`, a HAR you can import into Burp, an optional screenshot, and a `evidence.md` section ready to paste into `/report`. This is the proof layer the report pipeline expects (`skills/report-writing`, `commands/report.md`).
/poc capture https://api.target.com/v1/users/1 -H "Authorization: Bearer $TOK" \
--target target.com --vuln-class idor --severity high --finding-id F-12
/poc from-request req.txt --response resp.txt --target target.com --vuln-class idorRun directly:
# live: send the request (SSRF-guarded) and bundle it
tools/poc_bundler.py capture <url> -X GET -H "Cookie: session=..." \
--target t.com --vuln-class idor --severity high --finding-id F-12 --screenshot
# offline: bundle a saved raw request (e.g. copied out of Burp)
tools/poc_bundler.py from-request request.txt --response response.txt \
--target t.com --vuln-class idorA folder laid out exactly as `commands/report.md` expects:
findings/<target>-<vuln-class>/evidence/<finding-id>/ ├── request.http raw request you sent ├── response.http raw response that proves impact ├── repro.sh copy-paste curl reproduction ├── evidence.har HAR 1.2 — import into Burp / devtools ├── screenshot.png optional (best-effort via httpx) ├── evidence.md paste this into /report └── bundle.json manifest + response-body SHA-256
Bug bounty evidence carries **live auth** — session cookies, bearer tokens, API keys. By default every sensitive header (`Authorization`, `Cookie`, `Set-Cookie`, `X-Api-Key`, …) is **redacted** in all artifacts so the bundle is safe to paste into a report. `repro.sh` stays runnable by referencing each secret through an environment variable (`$AUTHORIZATION`, `$COOKIE`, …) instead of hardcoding it. Pass `--no-redact` only for local/personal use.
can't 302 the capture into cloud metadata or an internal host.
mutate production state), mirroring the autopilot `SafeMethodPolicy`.
tamper-evident; large bodies are truncated in the text artifacts but hashed in full.
Attach the bundle to its lead so nothing is lost:
lead_board.py touch <target> <lead_id> --status reported --finding-id F-12
The bundle's `evidence.md` and screenshots also surface automatically in the `/dashboard` findings view.
AI-powered bug bounty hunting toolkit that works with or without subscription.
Repo: shuvonsec/claude-bug-bounty
Show which external bug-bounty tools are installed on this machine and print install hints for the missing ones. Curated from high-signal repos. Use to…
Run autonomous hunt loop on a target — scope check → recon → rank surface → hunt → validate → report with configurable checkpoints. Usage: /autopilot…
HIBP k-anonymity check on a password wordlist. Enriches each password with its breach count, ranks DESC. Free API (no key), only first 5 chars of SHA-1 sent.…
Probe a 403/401 endpoint with the most-paid bypass tricks (header injection, path encoding, method swap, WAF fingerprint, vendor-specific). Wraps byp4xx when…
Build an exploit chain — given bug A, finds B and C to combine for higher severity and payout. Knows common chain patterns: IDOR→ATO, SSRF→cloud metadata,…
Sweep cloud assets for a target — public S3/Azure/GCP buckets via S3Scanner and cloud_enum, plus CloudFlare-bypassed origin IPs via CloudFail (or built-in…