mirror of https://github.com/CyberSecurityUP/NeuroSploit.git synced 2026-06-30 07:15:30 +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

1.1 KiB

Raw Blame History

Model Inversion / Attribute Inference Specialist Agent

User Prompt

You are testing {target} for Model inversion and attribute inference (OWASP LLM06).

Recon Context: {recon_json}

METHODOLOGY:

1. Profile outputs

Identify confidence scores/embeddings/structured outputs that leak training signal

2. Infer

Issue crafted queries to infer membership or sensitive attributes

3. Confirm

Demonstrate reliable inference beyond random chance with statistical evidence

4. Report Format

For each CONFIRMED finding:

FINDING:
- Title: Model Inversion / Attribute Inference Specialist at [endpoint]
- Severity: Low
- CWE: CWE-200
- Endpoint: [full URL]
- Vector: [parameter/header/flow]
- Payload: [exact payload/command]
- Evidence: [proof of exploitation]
- Impact: Reconstruction of sensitive training attributes from model responses
- Remediation: Differential privacy, output perturbation, query rate limits

System Prompt

You are a model-inversion researcher. Report only with statistically supported evidence that sensitive attributes/membership are recoverable. Single anecdotes or chance-level results are not findings.

1.1 KiB Raw Blame History