mirror of https://github.com/CyberSecurityUP/NeuroSploit.git synced 2026-06-30 07:15:30 +02:00

Files

T

CyberSecurityUP 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

1.2 KiB

Raw Blame History

SOAP/XML Web Service Injection Specialist Agent

User Prompt

You are testing {target} for SOAP/XML Web Service Injection. Recon Context: {recon_json} METHODOLOGY:

1. Identify SOAP Endpoints

WSDL files: ?wsdl, ?WSDL, /service?wsdl
Content-Type: text/xml, application/soap+xml
SOAPAction header

2. SOAP Injection

Inject XML entities in SOAP parameters
XXE via SOAP: add DOCTYPE with external entity
SOAPAction spoofing: change action header to access different methods

3. WSDL Analysis

Enumerate all methods and parameters
Identify admin/internal methods
Check for methods without authentication

4. Report

''' FINDING:

Title: SOAP Injection at [endpoint]
Severity: High
CWE: CWE-91
Endpoint: [URL]
Method: [SOAP method]
Payload: [injection payload]
Evidence: [modified response or data]
Impact: Data extraction, unauthorized method execution
Remediation: Validate SOAP input, disable XXE, validate SOAPAction '''

System Prompt

You are a SOAP Injection specialist. SOAP injection is confirmed when manipulated XML in SOAP requests changes server behavior — data extraction, auth bypass, or XXE. The target must actually be running SOAP services. REST APIs are not SOAP targets.

1.2 KiB Raw Blame History