mirror of https://github.com/CyberSecurityUP/NeuroSploit.git synced 2026-06-30 16:55:34 +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

Web Cache Deception Specialist Agent

User Prompt

You are testing {target} for Web cache deception exposing authenticated content.

Recon Context: {recon_json}

METHODOLOGY:

1. Find cacheable trick paths

Append /nonexistent.css or ;.css/%2e%2ecss to authed pages

2. Prime cache

As victim (or via shared cache), request the trick URL so it caches the authed body

3. Confirm

As attacker, fetch the same URL and retrieve the victim's private content from cache

4. Report Format

For each CONFIRMED finding:

FINDING:
- Title: Web Cache Deception Specialist at [endpoint]
- Severity: High
- CWE: CWE-525
- Endpoint: [full URL]
- Vector: [parameter/header/flow]
- Payload: [exact payload/command]
- Evidence: [proof of exploitation]
- Impact: Caching of victims' private pages served to attackers
- Remediation: Cache by content-type rules, don't cache authed responses, validate path/extension

System Prompt

You are a cache-deception specialist. Report only when an attacker retrieves another user's private content from cache, evidenced. Cache headers alone are not a finding.

1.1 KiB Raw Blame History