@cyberstrike-io/cyberstrike 1.1.10 → 1.1.11-beta.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (8) hide show
  1. package/README.md +54 -19
  2. package/package.json +12 -2
  3. package/web/assets/{ghostty-web-BEaItqWb.js → ghostty-web-BkjgiG2x.js} +1 -1
  4. package/web/assets/{home-BNJKducT.js → home-zYhRaV9C.js} +1 -1
  5. package/web/assets/{index-DTi-tKnC.js → index-BFKoq4fl.js} +15 -15
  6. package/web/assets/{index-qjnafwSF.css → index-BZMNDjFU.css} +1 -1
  7. package/web/assets/{session-D3tXjXUp.js → session-M7hPXNIo.js} +3 -3
  8. package/web/index.html +2 -2
package/README.md CHANGED
@@ -6,7 +6,7 @@
6
6
 
7
7
  <p align="center">
8
8
  Automated penetration testing from your terminal — plug in your Claude, GPT, or any LLM subscription<br>
9
- and turn it into an autonomous red team agent with 13+ specialized agents and 120+ OWASP test cases.
9
+ and turn it into an autonomous red team agent with 7,300+ security skills across MITRE ATT&CK, CIS, OWASP, and NIST.
10
10
  </p>
11
11
 
12
12
  <p align="center">
@@ -38,7 +38,7 @@
38
38
  npm i -g @cyberstrike-io/cyberstrike@latest && cyberstrike
39
39
  ```
40
40
 
41
- That's it. CyberStrike launches a TUI in your terminal, asks for your LLM provider and API key on first run, and you're ready to go. Tell it what to test — it handles reconnaissance, vulnerability discovery, exploitation, and reporting autonomously.
41
+ That's it. CyberStrike launches a TUI in your terminal, asks for your LLM provider and API key on first run, and you're ready to go. Tell it what to test — it loads relevant skills from 7,300+ MITRE ATT&CK, CIS, OWASP, and NIST test procedures, then handles reconnaissance, vulnerability discovery, exploitation, and reporting autonomously.
42
42
 
43
43
  > **Already have a Claude Code or OpenAI subscription?** CyberStrike's intelligence layer sits on top of your existing AI subscription. No separate API costs — your current plan powers an entire pentest toolkit.
44
44
 
@@ -82,15 +82,52 @@ CyberStrike isn't just a wrapper around an LLM. It's an intelligence layer that
82
82
 
83
83
  ---
84
84
 
85
+ ### Skills System — 7,300+ Actionable Security Tests
86
+
87
+ CyberStrike doesn't just give agents generic security knowledge — it loads domain-specific skills on-demand with zero context pollution.
88
+
89
+ **What's a skill?** A skill is a structured test procedure that includes:
90
+
91
+ - Target methodology (OWASP WSTG, MITRE ATT&CK, CIS Benchmark, NIST)
92
+ - Copy-paste ready test commands
93
+ - Tool references and dependencies
94
+ - Remediation guidance
95
+ - CWE mappings and severity ratings
96
+
97
+ **Coverage:**
98
+
99
+ | Framework | Skills | What It Includes |
100
+ | ------------------ | ------ | ----------------------------------------------------------------------------------- |
101
+ | **MITRE ATT&CK** | 691 | Enterprise tactics + 2,000+ Atomic Red Team tests (Kerberoasting, LSASS dump, etc.) |
102
+ | **CIS Benchmarks** | 1,500+ | Cloud (AWS/Azure/GCP), Containers (Docker/K8s), OS (Ubuntu), Server (Apache/Nginx) |
103
+ | **OWASP WSTG** | 125 | Web app security testing (XSS, SQLi, AuthN, AuthZ, Session, API) |
104
+ | **NIST** | 200+ | Security controls and compliance frameworks |
105
+
106
+ **Lazy Loading** — Skills load only when needed. An agent testing for Kerberoasting pulls T1558.003 skill (7 Atomic tests) into context, runs the tests, then discards it. Next test = new skill. Zero bloat.
107
+
108
+ **Search & Discovery** — Built-in skill search with relevance scoring. Query by keyword, tech stack, CWE ID, or category. 7,633 skills indexed in-memory.
109
+
110
+ ```bash
111
+ # Example: Agent loads T1558.003 Kerberoasting skill
112
+ Skill: T1558.003 - Kerberoasting
113
+ Tests: 7 Atomic Red Team test scenarios
114
+ Tools: Invoke-Kerberoast.ps1, Rubeus, setspn
115
+ Platforms: Windows
116
+ ```
117
+
118
+ Read more: [MITRE ATT&CK Integration](https://github.com/CyberStrikeus/CyberStrike/blob/main/.cyberstrike/skill/mitre_attack/), [CIS Benchmarks](https://github.com/CyberStrikeus/CyberStrike/tree/main/.cyberstrike/skill/CIS_benchmarks)
119
+
120
+ ---
121
+
85
122
  ### What Makes It Different
86
123
 
87
124
  <table>
88
125
  <tr>
89
126
  <td width="50%">
90
127
 
91
- **Specialized Security Agents, Not Generic Chat**
128
+ **7,300+ Security Skills, Not Generic Prompts**
92
129
 
93
- CyberStrike ships with 13+ agents purpose-built for security domains. Each agent carries domain-specific methodology, tool knowledge, and testing patterns. The web-application agent follows OWASP WSTG. The cloud-security agent knows CIS benchmarks. The mobile agent uses Frida and follows MASTG/MASVS. They don't guess — they follow proven offensive security frameworks.
130
+ CyberStrike agents don't improvise — they follow proven methodologies with lazy-loaded skills. Testing for Kerberoasting? Load T1558.003 (7 Atomic Red Team tests). Auditing Docker? Load CIS Docker v1.8.0 (118 controls). Agents pull exactly what they need, execute structured test procedures with copy-paste commands, then discard. Zero context pollution. Real pentest frameworks: MITRE ATT&CK, CIS Benchmarks, OWASP WSTG, NIST.
94
131
 
95
132
  </td>
96
133
  <td width="50%">
@@ -189,13 +226,12 @@ Bolt is CyberStrike's remote tool server. Deploy it on any VPS, cloud instance,
189
226
 
190
227
  CyberStrike connects to specialized MCP servers that extend its capabilities — **176+ security tools** across 5 domains:
191
228
 
192
- | Server | Tools | What It Adds |
193
- | ---------------------------------------------------------------------- | ----- | -------------------------------------------------------------------------- |
194
- | [hackbrowser-mcp](https://github.com/badchars/hackbrowser-mcp) | 39 | Browser-based security testing — XSS, CSRF, DOM manipulation, cookie theft |
195
- | [cloud-audit-mcp](https://github.com/badchars/cloud-audit-mcp) | 38 | Cloud security audits — 60+ checks across AWS, Azure, GCP |
196
- | [github-security-mcp](https://github.com/badchars/github-security-mcp) | 39 | GitHub security posture — repo, org, actions, secrets, supply chain |
197
- | [cve-mcp](https://github.com/badchars/cve-mcp) | 23 | CVE intelligence — NVD, EPSS, CISA KEV, GitHub Advisory, OSV |
198
- | [osint-mcp](https://github.com/badchars/osint-mcp) | 37 | OSINT recon — Shodan, VirusTotal, SecurityTrails, Censys, DNS, WHOIS |
229
+ | Server | Tools | What It Adds |
230
+ | ---------------------------------------------------------------------- | ----- | -------------------------------------------------------------------- |
231
+ | [cloud-audit-mcp](https://github.com/badchars/cloud-audit-mcp) | 38 | Cloud security audits — 60+ checks across AWS, Azure, GCP |
232
+ | [github-security-mcp](https://github.com/badchars/github-security-mcp) | 39 | GitHub security posture — repo, org, actions, secrets, supply chain |
233
+ | [cve-mcp](https://github.com/badchars/cve-mcp) | 23 | CVE intelligence — NVD, EPSS, CISA KEV, GitHub Advisory, OSV |
234
+ | [osint-mcp](https://github.com/badchars/osint-mcp) | 37 | OSINT recon — Shodan, VirusTotal, SecurityTrails, Censys, DNS, WHOIS |
199
235
 
200
236
  All open source. All installable with `npx`. Plug them into CyberStrike or use them standalone with any MCP-compatible client.
201
237
 
@@ -270,14 +306,13 @@ Read the [Contributing Guide](https://github.com/CyberStrikeus/CyberStrike/blob/
270
306
 
271
307
  CyberStrike is the core platform. These MCP servers extend its capabilities:
272
308
 
273
- | Project | Domain | Tools |
274
- | ---------------------------------------------------------------------- | --------------------------------------- | ------------------------------------- |
275
- | **CyberStrike** | **Autonomous offensive security agent** | **13+ agents, 120+ OWASP test cases** |
276
- | [hackbrowser-mcp](https://github.com/badchars/hackbrowser-mcp) | Browser-based security testing | 39 tools, Firefox, injection testing |
277
- | [cloud-audit-mcp](https://github.com/badchars/cloud-audit-mcp) | Cloud security (AWS/Azure/GCP) | 38 tools, 60+ checks |
278
- | [github-security-mcp](https://github.com/badchars/github-security-mcp) | GitHub security posture | 39 tools, 45 checks |
279
- | [cve-mcp](https://github.com/badchars/cve-mcp) | Vulnerability intelligence | 23 tools, 5 sources |
280
- | [osint-mcp](https://github.com/badchars/osint-mcp-server) | OSINT & reconnaissance | 37 tools, 12 sources |
309
+ | Project | Domain | Tools |
310
+ | ---------------------------------------------------------------------- | --------------------------------------- | ------------------------------------------- |
311
+ | **CyberStrike** | **Autonomous offensive security agent** | **7,300+ skills (MITRE, CIS, OWASP, NIST)** |
312
+ | [cloud-audit-mcp](https://github.com/badchars/cloud-audit-mcp) | Cloud security (AWS/Azure/GCP) | 38 tools, 60+ checks |
313
+ | [github-security-mcp](https://github.com/badchars/github-security-mcp) | GitHub security posture | 39 tools, 45 checks |
314
+ | [cve-mcp](https://github.com/badchars/cve-mcp) | Vulnerability intelligence | 23 tools, 5 sources |
315
+ | [osint-mcp](https://github.com/badchars/osint-mcp-server) | OSINT & reconnaissance | 37 tools, 12 sources |
281
316
 
282
317
  ---
283
318
 
package/package.json CHANGED
@@ -7,7 +7,7 @@
7
7
  "scripts": {
8
8
  "postinstall": "bun ./postinstall.mjs || node ./postinstall.mjs"
9
9
  },
10
- "version": "1.1.10",
10
+ "version": "1.1.11-beta.0",
11
11
  "license": "AGPL-3.0-only",
12
12
  "keywords": [
13
13
  "cyberstrike",
@@ -37,6 +37,16 @@
37
37
  "url": "https://github.com/CyberStrikeus/CyberStrike.git"
38
38
  },
39
39
  "optionalDependencies": {
40
- "@cyberstrike-io/cyberstrike-darwin-arm64": "1.1.10"
40
+ "@cyberstrike-io/cyberstrike-darwin-x64-baseline": "1.1.11-beta.0",
41
+ "@cyberstrike-io/cyberstrike-linux-arm64": "1.1.11-beta.0",
42
+ "@cyberstrike-io/cyberstrike-linux-x64-baseline": "1.1.11-beta.0",
43
+ "@cyberstrike-io/cyberstrike-darwin-arm64": "1.1.11-beta.0",
44
+ "@cyberstrike-io/cyberstrike-windows-x64-baseline": "1.1.11-beta.0",
45
+ "@cyberstrike-io/cyberstrike-linux-x64-musl": "1.1.11-beta.0",
46
+ "@cyberstrike-io/cyberstrike-linux-x64-baseline-musl": "1.1.11-beta.0",
47
+ "@cyberstrike-io/cyberstrike-linux-x64": "1.1.11-beta.0",
48
+ "@cyberstrike-io/cyberstrike-darwin-x64": "1.1.11-beta.0",
49
+ "@cyberstrike-io/cyberstrike-linux-arm64-musl": "1.1.11-beta.0",
50
+ "@cyberstrike-io/cyberstrike-windows-x64": "1.1.11-beta.0"
41
51
  }
42
52
  }