Bb Local Toolkit (Grade F)Güvenlik test edilmiş güvenlik testi becerisi Claude AI için. Not F. Tam bug bounty akışı — rekon (alt domainenumerasyonu, varlık keşfi, parmak izleme, HackerOne kapsamı, kaynak kodu inceleme), pre-hu

Why this exists?

Most bug‑hunting Claude setups are either too generic (one big "security" prompt) or too fragmented (you bookmark 30 disclosed reports and re‑read them every engagement). Neither scales past the second target. This bundle was built and validated through authorized engagements that exposed different capability gaps: Bug‑bounty engagement — surfaced four gaps a starter 3‑skill stack could not close: 1. No hypothesis discipline — drafts written before validation → wasted hours, hurt validity ratio 2. No per‑program reporting tactics — VRT defaults auto‑downgraded P3‑worthy findings to P4 3. No engagement coordination — findings, evidence, and submission IDs scattered across folders 4. No evidence hygiene — screenshots leaked cookies and victim PII External red‑team engagement — exposed five additional gaps that bug‑bounty defaults made worse: 1. Conservative defaults retracted real findings — WAPT mindset stopped tests early on defended targets where red‑team continuation would have surfaced bypass chains → redteam‑mindset 2. No mid‑engagement situational awareness — client SOC patched confirmed SQLi within 30 min; external attacker locked 14 accounts during a live test session — both invisible without explicit detection methodology → mid‑engagement‑ir‑detection 3. No enterprise‑platform attack chains — M365 + Entra ID, on‑prem SharePoint, Cisco SSL VPN, vCenter, and 7 Android APKs all needed current 2024‑2026 CVE knowledge and platform‑specific tradecraft → m365‑entra‑attack, .

Asked by Marcus Bell · Apr 3, 2026

Why your model switched mid‑session?

Separate from refusals, and easy to miss. On Opus 5, a narrow set of higher‑risk cyber requests — Anthropic names exploit generation, binary‑based vulnerability scanning and penetration testing — fall back to Opus 4.8 rather than being refused. You get a notice and the response is labelled with the model that answered, but in a long agentic run that is easy to scroll past, so it can look like Opus 5 quietly got worse. See why Claude switched models. What to do depends on what you are actually doing: | Situation | What helps | |---|---| | Auditing your own code — reviewing a repo you own for defects | Say so. "Defensive review of my own repo", "check this against the OWASP Top 10", "secure refactor to remediate" describe the work accurately and read as remediation. | | Authorized offensive work — live engagement, PoC for a bounty submission | This is what the bundle is for, and the supported route is CVP. Do not reword an offensive engagement to look defensive to get past a classifier — enroll instead. | | You just want the switching off | Settings → Capabilities disables automatic model switching. | /hunt states the engagement frame (authorized, scope‑bounded, remediable finding) on its first turn for exactly this reason — engagement context belongs in the session explicitly, not implied.

Asked by Noelia Campos · Mar 15, 2026

How it works?

A 6‑phase, non‑linear workflow — recon → map & rank → hunt → validate → report — with scope enforced in code and a 7‑Question Gate before anything is submitted. Two ways to drive it: Plain English — describe what you're testing and the relevant skill loads automatically. /hunt scaffold + cbh CLI — engagement‑folder structure, state, and orchestration. Includes a usage guide and worked example, a 6‑phase architecture & skill‑to‑phase map, and the cbh CLI.

Asked by Ravi Chandrasekaran · Mar 3, 2026

What's inside?

82 skills, auto‑loaded by topic — no invocation by name. Coverage across the external attack surface: | Category | # | Examples | |---|---|---| | Web application hunting | 13 | XSS, SQLi, SSRF, IDOR, LFI, SSTI, XXE, CSRF, CORS, open‑redirect | | Authentication & identity | 7 | auth‑bypass, session, OAuth, SAML, MFA‑bypass, ATO | | API & infrastructure | 15 | GraphQL, gRPC, WebSocket, API‑misconfig, host‑header, RCE | | Advanced & concurrency | 6 | race‑condition, HTTP smuggling, deserialization, cache‑poison | | Framework‑specific | 4 | Next.js, Node.js, Laravel, Spring Boot | | Enterprise identity & cloud ★ | 3 | M365/Entra, Okta, cloud‑IAM‑deep | | Infrastructure & appliance ★ | 4 | VMware vCenter, enterprise VPN, SharePoint, ASP.NET/NTLM | | Red‑team tradecraft ★ | 4 | redteam‑mindset, APK pipeline, supply‑chain recon, mid‑engagement IR | | Recon & OSINT | 4 | web2‑recon, offensive‑osint, subdomain | | Workflow, reporting & specialized | 11 | methodology, triage‑validation, evidence‑hygiene, VRT‑aware reporting | Full searchable catalog → docs/skills.md. Also ships 15 slash commands (/hunt, /recon, /report, …) and a deterministic engagement engine (engine/) that maps a target's attack surface and routes each finding to the skill that handles it.

Asked by Dumisani Ndlovu · Feb 13, 2026

What is this?

claude-bughunter is a drop-in skill bundle for the Claude Code skills system. Install once and Claude Code stops being a chatbot and starts behaving like a senior bug-hunting researcher or red‑team operator: it knows the techniques, the chain templates, the VRT mappings, the platform CVE chains, and the hygiene — and it stays in scope. Four layers stack: Think — bb‑methodology + redteam‑mindset: the 5‑phase non‑linear workflow, critical‑thinking framework, and red‑team operator discipline. Hunt webapps — 48 hunt‑skills curated from 681 disclosed HackerOne reports: per‑class detection patterns, payloads, bypass tables, and chain templates. Hit the perimeter — enterprise platform chains (M365/Entra, Okta, vCenter, SSL‑VPN appliances, SharePoint, cloud IAM): current 2024–2026 CVE chains + post‑credential escalation. Ship it — triage‑validation + reporting + evidence‑hygiene: the 7‑Question Gate, VRT‑aware severity, OOS rebuttals, PII redaction, and red‑team deliverables. All triggered automatically by topic — describe what you're testing in plain English and the relevant skill loads. No invocation by name.

Asked by Mireille Dupont · Jan 18, 2026