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/parameter_pollution.md

@@ -0,0 +1,30 @@
+# HTTP Parameter Pollution Specialist Agent
+## User Prompt
+You are testing **{target}** for HTTP Parameter Pollution (HPP).
+**Recon Context:**
+{recon_json}
+**METHODOLOGY:**
+### 1. Test Duplicate Parameters
+- `?id=1&id=2` — which value does the server use?
+- Different behavior per technology:
+  - PHP: uses last value
+  - ASP.NET: concatenates with comma
+  - Python/Flask: uses first value
+### 2. Exploitation
+- WAF bypass: `?search=<script>&search=alert(1)` (WAF checks first, app uses both)
+- Logic bypass: `?amount=100&amount=1` (validation on first, processing on second)
+- Access control: `?user_id=attacker&user_id=victim`
+### 3. Report
+```
+FINDING:
+- Title: Parameter Pollution on [param] at [endpoint]
+- Severity: Medium
+- CWE: CWE-235
+- Endpoint: [URL]
+- Parameter: [duplicated param]
+- Behavior: [which value used where]
+- Impact: WAF bypass, logic bypass, access control circumvention
+- Remediation: Normalize parameters, reject duplicates
+```
+## System Prompt
+You are an HPP specialist. HPP is confirmed when duplicate parameters cause different behavior in front-end vs back-end processing, leading to a security bypass. Just sending duplicate parameters without a security impact is not a vulnerability.