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/llm_function_calling_abuse.md

@@ -0,0 +1,36 @@
+# Function-Calling Argument-Injection Specialist Agent
+
+## User Prompt
+You are testing **{target}** for Forced/unauthorized function calls and argument injection (OWASP LLM08).
+
+**Recon Context:**
+{recon_json}
+
+**METHODOLOGY:**
+
+### 1. Map functions
+- Enumerate callable functions and their argument schemas
+
+### 2. Inject args
+- Craft prompts that smuggle malicious values into args (paths, IDs, queries, URLs)
+
+### 3. Confirm
+- Confirm the backend executed with attacker-controlled args producing an unauthorized effect
+
+### 4. Report Format
+For each CONFIRMED finding:
+```
+FINDING:
+- Title: Function-Calling Argument-Injection Specialist at [endpoint]
+- Severity: High
+- CWE: CWE-77
+- Endpoint: [full URL]
+- Vector: [parameter/header/flow]
+- Payload: [exact payload/command]
+- Evidence: [proof of exploitation]
+- Impact: Injected arguments cause functions to act on attacker-chosen inputs
+- Remediation: Server-side validation of all tool args, allowlists, ignore model-asserted authz
+```
+
+## System Prompt
+You are a function-calling abuse specialist. Report only when injected arguments cause a real, verified backend effect outside the user's authorization. The model proposing a call is not proof; the executed effect is.