Claude-Red v0.3.0 Released

Claude-Red is a library of drop-in SKILL.md files that turn Claude into a context-aware red team operator. Attack methodology loads on demand for authorized engagements, bug bounty work, and security assessments.

The project jumps from 37 to 78 skills across 23 categories in v0.3.0, adding full-spectrum coverage from container escapes to wireless protocol attacks.

## What's New

Major expansion - claude-red goes from 37 skills in flat directories to 78
skills across 23 organized categories. This release adds full-spectrum
offensive coverage from container escapes to wireless protocol attacks.

### 20 New Skills Across 10 Categories

- container/ - Docker/containerd breakout, runc CVEs, K8s RBAC abuse, etcd, kubelet API, pod escape
- cicd/ - GitHub Actions injection, Jenkins RCE, GitLab CI, secret extraction, OIDC federation
- api/ - OWASP API Top 10, REST/gRPC/WebSocket, batching attacks, webhook hijacking
- crypto/ - Padding oracle, ECB, hash extension, RSA, POODLE/DROWN/Heartbleed, pinning bypass
- privesc/ - Linux SUID/capabilities/sudo/kernel + Windows Potato family, DLL hijacking, UAC bypass
- post-exploitation/ - Lateral movement (PTH/PTT/NTLM relay), persistence (Golden/Silver tickets), data exfiltration (DNS/HTTPS/ICMP tunneling)
- forensics/ - Anti-forensics (timestomping, ADS, anti-VM) + C2 frameworks (Cobalt Strike, Sliver, Mythic, Havoc)
- supply-chain/ - Dependency confusion, typosquatting, build pipeline attacks
- social-engineering/ - GoPhish, EvilGinx2, MFA phishing, pretexting, vishing, USB drops
- network/ - ARP spoofing, LLMNR/NBT-NS poisoning, VLAN hopping, IPv6 attacks, MITM

### Wireless Suite - 14 Dedicated Skills

Split the monolithic offensive-wifi into per-surface skills covering the full
wireless attack surface:

wifi-recon, wpa2-psk, wpa3-sae, wpa-enterprise, wps, evil-twin,
krack-fragattacks, deauth-disassoc, bluetooth-ble, bluetooth-classic,
zigbee-thread-matter, z-wave, lorawan-sub-ghz, wifi (comprehensive)

### Deep Rewrites (2-4x More Content)

- offensive-deserialization - 183 -> 781 lines. Java/PHP/.NET/Python/Node/Ruby, K8s vectors, WAF bypass
- offensive-graphql - 207 -> 946 lines. Introspection bypass, batching, subscription abuse, CrackQL/BatchQL
- offensive-advanced-redteam - 146 -> 640 lines. C2 tradecraft, OPSEC, evasion, engagement planning
- offensive-ssti - 347 -> 758 lines. 10+ engine-specific exploits, filter bypass, blind exploitation, chaining

### Infrastructure & Tooling

- Skills reorganized into 23 category subdirectories
- claude-skills.json manifest for programmatic access
- install.sh one-liner installer
- convert_skills.py for Claude Console compatibility (community contribution)
- GitHub Actions: CodeQL scanning + automated skill review on PRs
- SECURITY.md, CONTRIBUTING.md, LICENSE (MIT)

Install into your skills directory:

git clone https://github.com/SnailSploit/claude-red ~/.claude/skills/claude-red

Full release notes are on the GitHub release page.

Happy hacking! :-)

• News
• Tools
• Ai