CalvinBackup/NeuroSploit
1
0
Fork 0
mirror of https://github.com/CyberSecurityUP/NeuroSploit.git synced 2026-08-10 19:50:20 +02:00
Code Issues Packages Projects Releases Wiki Activity
78 Commits 28 Branches 24 Tags
9dfcea87bcc2e42c5085d2a9c6a36291aba70708
Commit Graph
19 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
CyberSecurityUPandClaude Opus 4.8 9dfcea87bc docs: update README for v3.4.0 (Rust harness, whitebox, 249 agents, Gemini, intelligent selection) 
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-23 11:51:07 -03:00
CyberSecurityUPandClaude Opus 4.8 3ca3f269ee v3.4.x: intelligent agent selection, whitebox, recon/code agents, Gemini, artifacts, RL, XBOW GUI 
Harness intelligence:
- After recon, the model SELECTS which specialist agents match the target
  (select_agents) — runs the relevant subset, not blindly top-N
- RL reward store (rl.rs): per-agent weights persist to data/rl_state_rs.json,
  reward validated findings (severity-weighted), decay idle, bias next run
- Run artifacts persisted as JSON + MD (recon, exploitation transcript,
  findings, html report) under runs/<target>-<ts>/ for reuse by other AIs

Whitebox mode:
- run_whitebox: walks a repo, builds bounded source context, runs code agents,
  validates by adversarial vote. CLI `whitebox <path>` + web "White-box" mode

Agents: +12 recon (subdomain/tech/js/api/secrets/dns/content/param/waf/cloud/
graphql/osint) and +24 code SAST reviewers (sqli/cmdi/path/ssrf/xss/deser/
secrets/crypto/authz/idor/xxe/redirect/ssti/race/eval/csrf/random/logging/
upload/mass-assign/jwt/cors). Loader gains recon/ + code/ categories → 249 total

Models: +Google Gemini provider (API + gemini CLI subscription); installed_cli_
backends now detects gemini; chat_cli handles gemini/codex/grok + optional
Playwright MCP (.mcp.json) on the subscription path with autonomy flags

GUI: full XBOW-style redesign — sidebar (Operate/Library), topbar status, mode
segment (black-box/white-box), model panel, live console, severity cards,
agent browser with category filters, models view; responsive + aligned

Verified: cargo build --release clean; CLI agents/whitebox; LIVE subscription
run shows model selecting 23→4 agents, RL update, artifacts written; GUI +
white-box toggle in Playwright.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-23 11:39:56 -03:00
CyberSecurityUP bf56184912 Merge v3.4.0 subscription backend into main 2026-06-22 16:59:38 -03:00
CyberSecurityUPandClaude Opus 4.8 d59f28f36d v3.4.0: subscription backend (Claude Code / Codex / Grok logins) 
The Rust harness can now use models two ways:
- API: provider API key (OpenAI-compatible HTTP) — existing path
- Subscription: drive the locally-installed agentic CLI login directly, no API
  key (anthropic→claude, openai→codex, xai→grok)

- models.rs: ChatClient::chat_cli spawns the CLI (stdin prompt), cli_binary_for
  + installed_cli_backends + binary_in_path PATH detection
- pool.rs: ModelPool::with_auth(subscription); one() routes per model
- types/CLI: RunConfig.subscription + `run --subscription` flag
- web: /api/run honors "subscription"; /api/info reports detected cli_backends;
  SPA gets a "Use subscription" toggle

Verified live: `run --subscription --model anthropic:claude-haiku-4-5` drove the
Claude subscription end-to-end (recon + agent + vote) with no API key set.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-22 16:59:35 -03:00
CyberSecurityUPandClaude Opus 4.8 9c4f912323 chore: stop tracking generated report_rs.html 
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-21 21:33:42 -03:00
CyberSecurityUP a05a99e0f6 Merge NeuroSploit v3.4.0 — Rust multi-model harness into main 2026-06-21 19:59:33 -03:00
CyberSecurityUPandClaude Opus 4.8 56d3f0c723 NeuroSploit v3.4.0 — Rust multi-model harness + Axum dashboard 
New cargo workspace `neurosploit-rs/` (single `neurosploit` binary):

harness crate:
- models.rs: 11 OpenAI-compatible providers / 31 models (Claude, GPT, Grok,
  NVIDIA NIM, DeepSeek, Mistral, Qwen, Groq, Together, OpenRouter, Ollama)
- pool.rs: ModelPool with bounded concurrency, provider failover, and N-model
  validator voting (the panel doubles as the jury)
- agents.rs: loads the existing agents_md/ library (213 agents)
- pipeline.rs: recon → parallel exploit (semaphore-bounded) → N-model
  adversarial vote → score; streams live progress over a channel
- report.rs: HTML report
- tokio + reqwest(rustls); offline mode runs the pipeline without API keys

app binary:
- clap CLI: serve | run | agents | models  (run supports --model x N, --vote-n,
  --max-agents, --offline)
- axum web dashboard with multi-model panel, live console, findings, agent
  browser, embedded report; single binary serves the SPA (no npm/build)

Verified: cargo build clean; agents/models/offline-run CLI; server endpoints
(/api/info, /api/run lifecycle, /report); dashboard + live run in Playwright.

Docs: README v3.4.0 callout + RELEASE.md notes. target/ gitignored.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-21 19:58:43 -03:00
CyberSecurityUPandClaude Opus 4.8 a5badefc29 v3.3.0 GUI dashboard + reports + model expansion + root fix 
Engine:
- Fix: inject IS_SANDBOX=1 so Claude Code's --dangerously-skip-permissions
  works under root (real backend runs were exiting rc=1 immediately)
- models: expand to 40 models / 13 providers, tagged CLI vs API
  (NVIDIA NIM, DeepSeek, Mistral, Qwen/DashScope, Groq, Together, OpenRouter,
  Ollama, Gemini) — Qwen/DeepSeek/Llama usable via API
- backends: on_start callback surfaces the exact argv ("what runs behind it")
- orchestrator: require a Playwright screenshot per confirmed finding; collect
  results/activity.json; auto-generate reports after a run
- report.py: HTML always + PDF via Typst engine (.typ source emitted too)

Web dashboard (webgui/, stdlib only — no npm/build):
- Sidebar dashboard (PentAGI-style): Run / Agents / Insights / Reports / Settings
- Multi-target runs; live execution console + per-task activity; finding cards
  with screenshots; backend+provider+model pickers (CLI & API)
- Agents tab: browse 213 + add new .md agents from the UI
- Insights: interactive RL-weight + severity charts
- Reports: download/preview PDF + HTML
- Settings/API: execution mode, per-provider API keys, orchestrator, verbosity
- Endpoints: /api/agents (GET/POST), /api/rl, /api/config, /api/reports,
  /reports/* + /shots/* static serving

Cleanup: retire replaced web stack (frontend React, FastAPI backend, core
orchestration, old test) to legacy/. Active engine + GUI are fully standalone.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-14 23:26:11 -03:00
CyberSecurityUPandClaude Opus 4.8 22a7302a35 Add minimalist web GUI for the v3.3.0 engine 
Zero-dependency (stdlib http.server) front-end exposing only the essential
options — URL, backend, model, collaborator, RL + Playwright-MCP toggles — with
a live progress console. Calls neurosploit_agent directly; no npm/build.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-14 22:33:12 -03:00
CyberSecurityUP 3de357bf18 Merge NeuroSploit v3.3.0 — Autonomous MD-Agent Engine into main 
# Conflicts:
#	prompts/task_library.json
 2026-06-14 21:41:26 -03:00
CyberSecurityUPandClaude Opus 4.8 55af0d4634 NeuroSploit v3.3.0 — Autonomous MD-Agent Engine 
Re-model the pentest agent into an autonomous, markdown-driven engine that
turns a URL into a full engagement and delegates execution to a locally
installed agentic CLI backend.

Engine (neurosploit_agent/ + ./neurosploit launcher):
- orchestrator composes ONE master prompt from the agent library + RL weights
- backends: auto-detect & drive Claude Code / Codex / Grok CLI (+ Claude
  subscription); headless, autonomous, isolated workdir
- mcp: Playwright MCP (.mcp.json) for browser-based proof-of-execution
- rl: bounded per-agent reinforcement-learning weights w/ per-tech affinity,
  persisted to data/rl_state.json
- models: latest registry incl. NVIDIA NIM provider (PR #28)
- cli: interactive URL prompt + one-shot `run`, `backends`, `agents`, --dry-run

Agent library (agents_md/, 213 total):
- 196 vuln specialists incl. modern LLM/AI, cloud/K8s, API/auth, advanced
  injection, protocol smuggling, logic/crypto/supply-chain classes
- 17 meta-agents: orchestrator, recon, exploit_validator,
  false_positive_filter, severity_assessor, impact_evaluator, reporter,
  rl_feedback + migrated expert roles
- scripts/build_agents.py data-driven builder; REGISTRY.md index

Docs: rewritten README.md, v3.3.0 RELEASE.md, .env.example (NVIDIA NIM, xAI,
engine vars).

Retire legacy Python orchestration (neurosploit.py + agent classes) to legacy/.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-14 20:57:38 -03:00
CyberSecurityUPandClaude Opus 4.6 59f8f42d80 NeuroSploit v3.2.4 - MD Agent Orchestrator Overhaul + Claude 4.6 + SmartRouter Failover 
- MD Agent system restructured: real HTTP exploitation, retry with exponential backoff, reduced concurrency (2 parallel, 2s stagger)
- Claude 4.6 model support (Opus/Sonnet) with corrected API version headers
- SmartRouter true failover with provider preference cascade
- WAFResult attribute error fix in autonomous_agent.py
- CVSS data sanitization for all vulnerability database saves
- AI recon JSON parsing robustness improvements
- rebuild.sh simplified from 714 to 196 lines
- Frontend: removed unused routes, simplified Auto Pentest page
- Agent grid: reduced max tests per agent (8→5), condensed recon prompts

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-29 20:25:01 -03:00
CyberSecurityUPandClaude Opus 4.6 7563260b2b NeuroSploit v3.2.3 - Multi-Agent Security Testing Framework 
- Added 107 specialized MD-based security testing agents (per-vuln-type)
- New MdAgentLibrary + MdAgentOrchestrator for parallel agent dispatch
- Agent selector UI with category-based filtering on AutoPentestPage
- Azure OpenAI provider support in LLM client
- Gemini API key error message corrections
- Pydantic settings hardened (ignore extra env vars)
- Updated .gitignore for runtime data artifacts

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-16 18:59:22 -03:00
CyberSecurityUPandClaude Opus 4.6 e5857d00c1 NeuroSploit v3.2.2 - Full LLM Pentest Mode 
New feature: Full LLM Pentest mode where the AI drives the entire
penetration test cycle autonomously. The LLM plans HTTP requests,
the system executes them, and the LLM analyzes real responses to
identify vulnerabilities — like a human pentester using Burp Suite.

- New OperationMode.FULL_LLM_PENTEST + AgentMode enum
- _run_full_llm_pentest(): 30-round ReACT loop (plan→execute→analyze→adapt)
- 3 new prompt functions in ai_prompts.py (system, round, report)
- Anti-hallucination: findings without real evidence are rejected
- All findings routed through ValidationJudge pipeline
- FullIATestingPage updated: 4-phase UI (Recon→Testing→PostExploit→Report)
- No Kali sandbox required — uses system HTTP client directly
- Methodology injection from pentestcompleto_en.md (118KB)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-24 00:28:26 -03:00
CyberSecurityUPandClaude Opus 4.6 79acfe04a3 NeuroSploit v3.2.1 - AI-Everywhere Auto Pentest + Container Fix + Deep Recon Overhaul 
## AI-Everywhere Auto Pentest
- Pre-stream AI master planning (_ai_master_plan) runs before parallel streams
- Stream 1 AI recon analysis (Phase 9: hidden endpoint probing, priority routing)
- Stream 2 AI payload generation (replaces hardcoded payloads with context-aware AI)
- Stream 3 AI tool output analysis (real findings vs noise classification)
- 4 new prompt builders in ai_prompts.py (master_plan, junior_ai_test, tool_analysis, recon_analysis)

## LLM-as-VulnEngine: AI Deep Testing
- New _ai_deep_test() iterative loop: OBSERVE→PLAN→EXECUTE→ANALYZE→ADAPT (3 iterations max)
- AI-first for top 15 injection types, hardcoded fallback for rest
- Per-endpoint AI testing in Phase C instead of single _ai_dynamic_test()
- New system prompt context: deep_testing + iterative_testing
- Token budget adaptive: 15 normal, 5 when <50k tokens remain

## Container Fix (Critical)
- Fixed ENTRYPOINT ["/bin/bash", "-c"] → CMD ["bash"] in Dockerfile.kali
- Root cause: Docker ran /bin/bash -c "sleep" "infinity" → missing operand → container exit
- All Kali sandbox tools (nuclei, naabu, etc.) now start and execute correctly

## Deep Recon Overhaul
- JS analysis: 10→30 files, 11 regex patterns, source map parsing, parameter extraction
- Sitemaps: recursive index following (depth 3), 8 candidates, 500 URL cap
- API discovery: 7→20 Swagger/OpenAPI paths, 1→6 GraphQL paths, request body schema extraction
- Framework detection: 9 frameworks (WordPress, Laravel, Django, Spring, Express, ASP.NET, Rails, Next.js, Flask)
- 40+ common hidden/sensitive paths checked (.env, .git, /actuator, /debug, etc.)
- API pattern fuzzing: infers endpoints from discovered patterns, batch existence checks
- HTTP method discovery via OPTIONS probing
- URL normalization and deduplication

## Frontend Fixes
- Elapsed time now works for completed scans (computed from started_at→completed_at)
- Container telemetry: exit -1 shows "ERR" (yellow), duration shows "N/A" on failure
- HTML report rewrite: professional pentest report with cover page, risk gauge, ToC, per-finding cards, print CSS

## Other
- Updated rebuild.sh summary and validation
- Bug bounty training datasets added

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-23 17:55:28 -03:00
CyberSecurityUP b056f6962a Merge main into v3.2 (ours strategy) - prepare main override 
Merging main history to maintain lineage before replacing main
with v3.2 content. The v3.2 branch is the definitive release.
 2026-02-22 18:09:27 -03:00
CyberSecurityUPandClaude Opus 4.6 9f47108876 Fix: remove last gpt-4-turbo-preview fallback in generate() method 
Missed occurrence in the OpenAI chat.completions.create() call
inside generate(). Now uses gpt-4o consistently.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-22 18:05:26 -03:00
CyberSecurityUPandClaude Opus 4.6 4041018397 Fix: OpenRouter/Together/Fireworks detection + deprecated gpt-4-turbo-preview model 
Issues fixed:
- OpenRouter API key not recognized: _set_no_provider_error() now checks all 7
  provider keys (was only checking Anthropic/OpenAI/Google), so users with only
  OPENROUTER_API_KEY set no longer get "No API keys configured" error
- Error message now lists all 8 providers (added OpenRouter, Together, Fireworks)
  instead of only 5 (Anthropic, OpenAI, Google, Ollama, LM Studio)
- gpt-4-turbo-preview (deprecated by OpenAI, 404 error) replaced with gpt-4o
  as default OpenAI model in LLMClient init and generate() fallback
- Settings API model list updated: removed gpt-4-turbo-preview and o1-preview/mini,
  added gpt-4.1, gpt-4.1-mini, o3-mini
- .env.example comment updated to reference gpt-4o instead of gpt-4-turbo

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-22 18:04:43 -03:00
CyberSecurityUP e0935793c5 NeuroSploit v3.2 - Autonomous AI Penetration Testing Platform 
116 modules | 100 vuln types | 18 API routes | 18 frontend pages

Major features:
- VulnEngine: 100 vuln types, 526+ payloads, 12 testers, anti-hallucination prompts
- Autonomous Agent: 3-stream auto pentest, multi-session (5 concurrent), pause/resume/stop
- CLI Agent: Claude Code / Gemini CLI / Codex CLI inside Kali containers
- Validation Pipeline: negative controls, proof of execution, confidence scoring, judge
- AI Reasoning: ReACT engine, token budget, endpoint classifier, CVE hunter, deep recon
- Multi-Agent: 5 specialists + orchestrator + researcher AI + vuln type agents
- RAG System: BM25/TF-IDF/ChromaDB vectorstore, few-shot, reasoning templates
- Smart Router: 20 providers (8 CLI OAuth + 12 API), tier failover, token refresh
- Kali Sandbox: container-per-scan, 56 tools, VPN support, on-demand install
- Full IA Testing: methodology-driven comprehensive pentest sessions
- Notifications: Discord, Telegram, WhatsApp/Twilio multi-channel alerts
- Frontend: React/TypeScript with 18 pages, real-time WebSocket updates
 2026-02-22 17:59:28 -03:00