Radar / AI security / Claude-BugHunter
Claude-BugHunter: 83 skills that turn Claude Code into a bug-bounty hunter
A Claude Code skill bundle distilled from 681 disclosed HackerOne reports across 24 vulnerability classes, plus enterprise identity and infrastructure attack matrices; #1 on GitHub Trending with 10,400+ stars.
Why it matters
The fastest-moving security skill bundle of the week — public vulnerability reports turned into auditable agent skills that run on five coding harnesses, gaining about 1,000 stars a day.
What you could build with it
A security researcher could point Claude Code at an in-scope bug-bounty target and get a structured hunt — recon, a ranked attack surface, and validated findings with severity scoring — instead of ad-hoc prompting.
Does it hold up?
Battle-tested across authorized red-team engagements and public training platforms (DVWA, OWASP Juice Shop, Hacker101) per the README, with a 7-question authorization gate before any submission — but it is explicitly external-surface only, and Anthropic's runtime safeguards can block exploitation steps mid-session.
Built with Claude-BugHunter
- Turn Claude Code into a bug bounty hunter: hands-on with Claude-BugHunterarticle · Hands-on tutorial: installs the bundle, scaffolds a practice engagement, runs a first hunt against OWASP Juice Shop, and puts a finding through the 7-question validation gate.
- 83 skills that turn Claude Code into a disciplined bug hunterarticle · Writeup of the bundle's design: chain templates from 681 paid-out reports, scope enforced in code, and the deliberate exclusion of internal AD attacks and C2 tooling.
- Offense takes the top spot: GitHub trending, day 279medium · Daily GitHub trending diary for Nov 18: Claude-BugHunter moved to #1 on the board at 10,113 stars, gaining about 1,005 a day.
Learn more
First spotted on github: source.
More AI security
Codex Security 0.10.0: OpenAI's agentic vulnerability scanner adds resumable scans and cost budgetsOpenAI released Codex Security 0.10.0 on 12 Nov 2026: the open-source CLI and TypeScript SDK that builds a threat…security · JEV 0.69ARTEX: the open-source AI pentesting framework the FBI just warned aboutA self-hosted, LLM-driven penetration-testing platform: a planner agent splits a goal into intents, worker agents run…security · JEV 0.67Claude-Cage: a lightweight VM that stops Claude leaking to the networkA lightweight virtual machine built for Claude that blocks network leaks, with multi-platform support, multi-account…security · JEV 0.59Detectify Agentic Tooling: prove what your AI security agent actually testedDetectify's new tooling lets an organization's own AI agents investigate suspected vulnerabilities against live…security · JEV 0.3Puffin: identity and inboxes for AI agentsIdentity and inboxes for AI agents: a real email address, calendar, and chat seats per agent.security · JEV 0.2MAI Cyber 2 Flash: Microsoft's security model matches GPT-6 Astra at under 2% of the costMicrosoft's specialist security model scores 92.3% on CyberGym-E2E with a 1M-token context at $0.10/$0.50 per million…security · JEV 0.19
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.