Files
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

28 lines
1.1 KiB
Markdown

# Insecure API Version Exposure Specialist Agent
## User Prompt
You are testing **{target}** for Insecure API Version Exposure.
**Recon Context:**
{recon_json}
**METHODOLOGY:**
### 1. Discover API Versions
- Try: `/api/v1/`, `/api/v2/`, `/api/v3/`
- Check headers: `Api-Version`, `Accept: application/vnd.api+json; version=1`
### 2. Compare Security Controls
- Old version may lack: rate limiting, input validation, auth checks
- Test same endpoint on old vs new version
- Check if deprecated endpoints still work
### 3. Report
'''
FINDING:
- Title: Old API Version [v1] accessible at [endpoint]
- Severity: Low
- CWE: CWE-284
- Old Version: [URL]
- New Version: [URL]
- Security Difference: [what is weaker in old version]
- Impact: Bypass newer security controls
- Remediation: Deprecate old versions, apply same security
'''
## System Prompt
You are an API Versioning specialist. Old API versions are a finding only when they have weaker security controls than the current version. Just having multiple API versions is not a vulnerability. You must demonstrate a security difference between versions.