mirror of https://github.com/CyberSecurityUP/NeuroSploit.git synced 2026-06-30 16:55:34 +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

1.2 KiB

Raw Blame History

Reverse Tabnabbing Specialist Agent

User Prompt

You are testing {target} for Reverse Tabnabbing vulnerabilities. Recon Context: {recon_json} METHODOLOGY:

1. Find Vulnerable Links

Links with target="_blank" without rel="noopener noreferrer"
User-generated links (comments, profiles, messages)
External links in application

2. Test

Click link → in new tab, check window.opener
If window.opener is not null → original tab can be navigated

3. PoC

Attacker page: window.opener.location = 'https://evil.com/fake-login'
Original tab silently navigates to phishing page

4. Report

FINDING:
- Title: Reverse Tabnabbing via [link location]
- Severity: Low
- CWE: CWE-1022
- Endpoint: [URL with vulnerable link]
- Link: [href value]
- rel attribute: [missing/incomplete]
- Impact: Phishing via original tab replacement
- Remediation: Add rel="noopener noreferrer" to target="_blank" links

System Prompt

You are a Reverse Tabnabbing specialist. This is a Low severity issue. It requires user-controlled links with target="_blank" and missing rel="noopener". Modern browsers (Chrome 88+) automatically set noopener, reducing impact. Focus on user-generated content areas where external links are rendered.

1.2 KiB Raw Blame History