pentesting 0.7.32 → 0.7.33

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 (2) hide show
  1. package/README.md +53 -18
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -35,26 +35,61 @@ pentesting
35
35
 
36
36
  ---
37
37
 
38
- ## Features
38
+ ## 🧠 Philosophy: Think Like a Hacker
39
+
40
+ **Pentesting is not a brute-force tool.** It's an intelligent agent that thinks strategically.
41
+
42
+ ### Strategic Decision Framework
43
+
44
+ Every action is evaluated using:
45
+
46
+ ```
47
+ Value = (Probability × CVSS Impact) / Time Cost
48
+ ```
49
+
50
+ The agent only executes actions with **confidence >50%**. Below that, it finds a better approach.
51
+
52
+ ### Self-Reflection Before Every Action
53
+
54
+ Before running any tool, the agent asks:
55
+ - "What exactly am I trying to learn?"
56
+ - "Is this the FASTEST way to get that information?"
57
+ - "Have I already tried this? What happened?"
58
+ - "Is there a simpler approach?"
59
+
60
+ ### Mandatory Fallback Strategy
61
+
62
+ When a tool fails, the agent immediately tries alternatives:
63
+
64
+ | Task | Primary | Fallback 1 | Fallback 2 |
65
+ |------|---------|------------|------------|
66
+ | Subdomain | subfinder | ffuf | amass |
67
+ | Directory | gobuster | ffuf | dirsearch |
68
+ | Port Scan | rustscan | nmap | masscan |
69
+
70
+ ---
71
+
72
+ ## 🔥 Why Pentesting?
73
+
74
+ | Feature | Traditional Tools | Pentesting Agent |
75
+ |---------|-------------------|------------------|
76
+ | Decision Making | Manual | AI-driven with confidence scoring |
77
+ | Tool Selection | You choose | Auto-selects based on context |
78
+ | Failure Handling | You retry | Auto-fallback to alternatives |
79
+ | Attack Planning | Manual prioritization | CVSS-based priority matrix |
80
+ | Context Awareness | None | Remembers all findings |
81
+ | Reporting | Manual | Auto-generated findings |
82
+
83
+ ---
84
+
85
+ ## ✨ Core Capabilities
39
86
 
40
- ### Core Capabilities
41
- - **Intelligent Agent**: Self-reflection and decision framework (inspired by Claude Code)
42
- - **Confidence Scoring**: Only acts on actions with >50% success probability
43
87
  - **10-Phase Attack Workflow**: Recon → Scan → Enum → Vuln Analysis → Exploitation → PrivEsc → Pivot → Persist → Exfil → Report
44
- - **Auto Docker Management**: Automatically pulls and starts `pentesting-tools` container
45
- - **Multi-Target Attack**: Register multiple targets and attack them sequentially
46
- - **Real-time Feedback**: See thinking process, tool calls, and results live
47
- - **ESC Interrupt**: Stop execution anytime with ESC key
48
- - **Rainbow Spinner**: Visual feedback with cycling colors
49
-
50
- ### v0.7.16 New Features
51
- - **Self-Reflection**: Agent asks "Is this the fastest way?" before every action
52
- - **Decision Framework**: Value = (Probability × Impact) / Time Cost
53
- - **Concrete Tool Commands**: Exact ffuf, nmap, hydra syntax with wordlist paths
54
- - **Auto Docker**: Container starts automatically when tools are missing
55
- - **Thinking Display**: See `[thinking]` and `[reasoning]` messages
56
- - **Token Label**: Status bar shows `3k tok` instead of just `3k`
57
- - **Approval Fix**: "Approve always" now works correctly (no repeat prompts)
88
+ - **Auto Docker Management**: Pulls and starts tool container automatically
89
+ - **Multi-Target Attack**: Attack multiple targets sequentially
90
+ - **Real-time Feedback**: See thinking process, tool calls, results live
91
+ - **Session Persistence**: Save/resume attack sessions
92
+ - **Context Compaction**: Automatic history summarization
58
93
 
59
94
  ---
60
95
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "pentesting",
3
- "version": "0.7.32",
3
+ "version": "0.7.33",
4
4
  "description": "Autonomous Penetration Testing AI Agent",
5
5
  "type": "module",
6
6
  "main": "dist/index.js",