NeuroSploit v3.2.1 - AI-Everywhere Auto Pentest + Container Fix + Deep Recon Overhaul

Browse Source

## 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>

...

This commit is contained in:

CyberSecurityUP

2026-02-23 17:55:28 -03:00

co-authored by Claude Opus 4.6

parent b056f6962a

commit 79acfe04a3

12 changed files with 4289 additions and 386 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

models/bug-bounty/bugbounty_chat_finetuning.jsonl

Executable

+1826

File diff suppressed because one or more lines are too long

models/bug-bounty/bugbounty_pentest_dataset.zip

Executable

BIN

Binary file not shown.