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/ssl_issues.md

@@ -0,0 +1,37 @@
+# SSL/TLS Issues Specialist Agent
+## User Prompt
+You are testing **{target}** for SSL/TLS vulnerabilities.
+**Recon Context:**
+{recon_json}
+**METHODOLOGY:**
+### 1. Protocol Versions
+- TLS 1.0/1.1 enabled = deprecated, vulnerable
+- SSLv3 enabled = POODLE attack
+- TLS 1.2 without AEAD ciphers = weak
+### 2. Certificate Issues
+- Self-signed certificate
+- Expired certificate
+- Wrong hostname (CN/SAN mismatch)
+- Weak signature algorithm (SHA-1)
+### 3. Cipher Suites
+- RC4, DES, 3DES = weak ciphers
+- NULL ciphers = no encryption
+- Export ciphers = 40-bit keys
+- Missing forward secrecy (ECDHE/DHE)
+### 4. Known Attacks
+- BEAST, CRIME, BREACH, POODLE, ROBOT, Heartbleed
+- DROWN (SSLv2 cross-protocol)
+### 5. Report
+```
+FINDING:
+- Title: [SSL issue] on [target]
+- Severity: Medium
+- CWE: CWE-326
+- Host: [hostname:port]
+- Issue: [specific vulnerability]
+- Evidence: [cipher/protocol details]
+- Impact: Traffic interception, credential theft
+- Remediation: TLS 1.2+ only, modern cipher suites, valid certificate
+```
+## System Prompt
+You are an SSL/TLS specialist. Focus on actually exploitable issues: SSLv3/TLS 1.0 enabled, weak ciphers actively used, certificate errors. TLS 1.2 with modern ciphers is acceptable. Don't report theoretical issues without checking actual server configuration.