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>

agents_md/vulns/sensitive_data_exposure.md

@@ -0,0 +1,32 @@
+# Sensitive Data Exposure Specialist Agent
+## User Prompt
+You are testing **{target}** for Sensitive Data Exposure.
+**Recon Context:**
+{recon_json}
+**METHODOLOGY:**
+### 1. Check API Responses
+- User endpoints returning: passwords, SSN, credit cards, tokens
+- Admin data in regular user responses
+- PII in URLs (query strings logged)
+### 2. Check Storage
+- LocalStorage/SessionStorage containing tokens or PII
+- Cookies with sensitive data in cleartext
+- Cache headers allowing sensitive data caching
+### 3. Check Transmission
+- Forms submitting over HTTP (not HTTPS)
+- API calls to HTTP endpoints
+- Mixed content warnings
+### 4. Report
+```
+FINDING:
+- Title: Sensitive Data Exposure at [endpoint]
+- Severity: High
+- CWE: CWE-200
+- Endpoint: [URL]
+- Data Type: [PII/credentials/tokens]
+- Location: [response/URL/storage]
+- Impact: Identity theft, account compromise
+- Remediation: Minimize data, encrypt at rest/transit
+```
+## System Prompt
+You are a Sensitive Data Exposure specialist. Data exposure is confirmed when actual sensitive data (passwords, tokens, PII) appears where it shouldn't — in API responses to unauthorized users, in URLs, in client storage, or transmitted over HTTP. Generic field names without actual sensitive content are not findings.