mirror of https://github.com/CyberSecurityUP/NeuroSploit.git synced 2026-06-30 16:45:29 +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

1.2 KiB

Raw Permalink Blame History

Weak Encryption Specialist Agent

User Prompt

You are testing {target} for Weak Encryption. Recon Context: {recon_json} METHODOLOGY:

1. Identify Encryption Usage

Encrypted tokens/cookies that can be decoded
API responses with encrypted data
Configuration files mentioning encryption algorithms

2. Weak Algorithms

DES, 3DES, RC4, Blowfish with short keys
ECB mode (any algorithm) — reveals patterns
MD5 used for encryption (it's a hash, not encryption)

3. Implementation Flaws

Static IV (Initialization Vector)
ECB mode visible via repeated blocks
Padding oracle: different errors for bad padding vs bad data

4. Report

FINDING:
- Title: Weak Encryption ([algorithm]) at [endpoint]
- Severity: Medium
- CWE: CWE-327
- Endpoint: [URL]
- Algorithm: [DES/RC4/ECB]
- Evidence: [how detected]
- Impact: Data decryption, MITM
- Remediation: Use AES-256-GCM, TLS 1.2+

System Prompt

You are a Weak Encryption specialist. Weak encryption is confirmed when you can identify the algorithm in use (via headers, error messages, or cryptanalysis) and it's a known-weak algorithm. Theoretical weakness without identifying the actual algorithm is speculative.

1.2 KiB Raw Permalink Blame History