By kalpmodi
Run AI-guided, phase-chained penetration tests and bug bounty hunts: initialize targets, perform recon and subdomain enumeration, hunt secrets and API keys, test web/API vulns like SQLi/XSS/SSRF/race conditions/OAuth, audit cloud/AD infra misconfigs, exploit chains, triage findings with precision gating, and generate Markdown reports.
Use when encountering HTTP 403 Forbidden responses during pentests or bug bounty hunting, testing access control bypasses, trying to reach restricted endpoints, admin panels, or protected API routes. Also trigger when the user says "403 bypass", "bypass forbidden", "access denied bypass", "forbidden page bypass", or "trying to access restricted endpoint". Use this whenever a 403 needs to be tested - not just blindly accepted.
Internal utility library - not an invokable skill. Contains phase0.sh (session state, intel relay, memory read) and signals.sh (append-only signal emission). Sourced by all other skills via `source ~/.claude/skills/_shared/phase0.sh`.
Use when attacking Active Directory environments, hunting Kerberoastable accounts, AS-REP roasting, DCSync, Pass-the-Hash, Pass-the-Ticket, BloodHound path analysis, LDAP enumeration, GPO abuse, ACL abuse, or full AD domain compromise chains. Also use when the user says "attack AD", "domain compromise", "Kerberoast", "DCSync", "BloodHound", or "lateral movement".
Use when auditing cloud infrastructure for misconfigurations, testing AWS IAM privilege escalation, enumerating exposed S3 buckets, attacking GCP service accounts, testing Azure RBAC misconfigs, hunting for exposed Kubernetes API servers, or finding cloud credential leaks in metadata services. Also use when the user says "cloud audit", "AWS pentest", "GCP attack", "K8s attack", "S3 exposed", "metadata service", or "cloud misconfiguration".
Use when context is running long during a pentest engagement, at phase boundaries after completing a full phase, or when the user says "compact", "compress context", "trim context", or "save tokens". Compresses completed phase outputs while keeping session.json as the authoritative source of truth.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
An AI pentest co-pilot that runs natively inside Claude Code, Gemini CLI, Cursor, or any agent. It is not a wrapper around automated scanners. It is a structured reasoning system for finding what scanners miss: logic flaws, architecture leaks, supply chain vectors, cryptographic weaknesses, and chained attacks.
Core constraint: Every finding requires a reproducible HTTP response body containing sensitive data. No evidence = no finding. OOB callback alone is never Critical.
/plan-engagement → /recon → /secrets → /exploit → /zerodayhunt → /triage → /report
┌─────────────────────────────────────────────────────────────────────┐
│ session.json (state bus) │
│ ┌──────────────┐ ┌──────────────┐ ┌───────────────────────────┐ │
│ │ engagement │ │ intel_relay │ │ scalpel │ │
│ │ .state │ │ .from_recon │ │ .hypotheses[] │ │
│ │ .target │ │ .from_secrets│ │ .active_manifest │ │
│ │ .scope │ │ .from_exploit│ │ .doom_loop.technique_runs │ │
│ └──────────────┘ │ .from_cloud │ │ .snr.signal_count │ │
│ │ .from_redteam│ └───────────────────────────┘ │
│ ┌──────────────┐ └──────────────┘ ┌───────────────────────────┐ │
│ │ report_draft │ ┌──────────────┐ │ signals.jsonl │ │
│ │ .findings[] │ │ intel │ │ (append-only, race-proof) │ │
│ │ .chains[] │ │ .technologies│ │ {type,value,source,conf} │ │
│ └──────────────┘ │ .live_hosts │ └───────────────────────────┘ │
│ │ .credentials │ │
│ └──────────────┘ │
└─────────────────────────────────────────────────────────────────────┘
▲ read/write ▲ read/write
│ │
┌────────┴────────────────────────┴──────────────────────────────────┐
│ _shared/phase0.sh │
│ p0_init_vars() p0_state_gate() p0_read_relay() │
│ p0_read_memory() p0_read_hypotheses() p0_manifest_write() │
│ p0_relay_write() p0_relay_append() p0_completion_gate() │
└────────────────────────────────────────────────────────────────────┘
▲ source ▲ source
│ │
┌────────┴──────────┐ ┌─────────┴────────────────────────────────┐
│ Thin Router │ │ Technique Library (tech/*.md) │
│ SKILL.md │ │ loaded on demand via manifest priority │
│ ~180 lines │ │ ~80 lines each │
│ - Phase 0 │ │ ssrf-oob.md | jwt-saml-sso.md │
│ - Manifest build │ │ chain-blueprints.md | client-proto.md │
│ - Loader table │ │ ...68 total across 4 split skills │
└───────────────────┘ └──────────────────────────────────────────┘
npx claudepluginhub kalpmodi/akira71-skill bug-hunting & external red-team bundle for Claude Code — 48 hunt-* web/vuln-class + framework skills, enterprise platform attack chains (M365/Entra, Okta, SharePoint, vCenter, SSL-VPN, APK), recon/OSINT, reporting & validation gates, and Burp MCP integration. Skills auto-load by topic; 15 slash commands included.
Full penetration testing framework - 100+ attack categories covering OWASP, injection, authentication, cloud, and more
Claude Code skills and agents for authorized security testing, bug bounty hunting, and pentesting workflows
Complete offensive security operator workspace: 27 specialist agents, 6 engagement commands, 5 reference skill libraries, scope-gated hooks, and evidence logging for professional penetration testing and red-team operations.
872 on-demand security skills for CTF, pentest, bug bounty, DFIR, detection engineering, cloud, identity, and red/blue team work. Skills are plain Markdown and activate by task without permanently consuming context. Bundles vendored skills under mixed licenses (MIT, Apache-2.0, CC-BY-SA-4.0) — see per-source attribution in .claude/skills/SKILLS.md.
183+ pentesting and OSINT tools (nmap, nuclei, amass, subfinder, httpx, sherlock, maigret, trufflehog, sqlmap, impacket, and more) wired into Claude Code as a single skill. Runs locally on any OS via native Bash, WSL, or purpose-built Docker images (instrumentisto/nmap, projectdiscovery/nuclei, caffix/amass, etc.). Just ask Claude to recon a target, scan a network, investigate a username, or chain OSINT workflows — the skill picks the right backend and image automatically.