mirror of
https://github.com/CyberSecurityUP/NeuroSploit.git
synced 2026-09-29 04:21:44 +02:00
CyberSecurityUPandClaude Opus 5
c3de51d508
Integrates TypeSafe's System One model (Jev) as an optional, calibrated
adjudicator — the RLCD (Reinforcement Learning for Calibrated Decisions) tier:
typed judgments with probabilities where the harness needs a number, not prose.
- typesafe.rs: HTTP client for POST /v1/systemone (Bearer TYPESAFE_API_KEY,
model jev-latest), with Choice/Noul/Score primitives, retry on 429/529, and
parsed answers exposing the probability distribution + confidence.
adjudicate() asks a Choice {confirmed/needs-review/rejected} plus an
impact-demonstrated Noul over a finding; calibrated_confidence() folds
demonstrated impact into the number, wants_review() gates a split distribution.
- pipeline: an optional pass (runs when TYPESAFE_API_KEY is set, off with
NEUROSPLOIT_TYPESAFE=off) adjudicates each finding over its EVIDENCE — never
its narrative — refining confidence and the needs-review boundary. Additive:
a deterministic validator still rules; TypeSafe can only lower confidence or
flag for review, never resurrect a rejected claim. Audited per finding.
- env.example + README document it; the web console inherits the key via env.
Where the model stack maps in NeuroSploit: LM/BERT ≈ the deterministic
validators (no model), RLHF chat ≈ the exploit/recon agents, RLVR reasoning ≈
the DeepReasoning budget tier, RLCD ≈ this calibrated adjudication.
373 tests (+5).
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
78 lines
2.8 KiB
Bash
Executable File
78 lines
2.8 KiB
Bash
Executable File
# NeuroSploit v3.5.1 — environment / API keys (optional)
|
|
# ------------------------------------------------------------------
|
|
# You only need this for the API-key auth path. If you log in with a
|
|
# local subscription CLI instead (--subscription with Claude / Codex /
|
|
# Gemini / Grok), you don't need any key here.
|
|
#
|
|
# Set the key(s) for the providers you use, then load and run:
|
|
# set -a; . ./.env; set +a
|
|
# neurosploit run http://target --model anthropic:claude-opus-4-8 -v
|
|
#
|
|
# Provider prefix -> env var (use as `--model <prefix>:<model>`).
|
|
|
|
# anthropic: https://console.anthropic.com/
|
|
ANTHROPIC_API_KEY=
|
|
|
|
# openai: https://platform.openai.com/api-keys
|
|
OPENAI_API_KEY=
|
|
|
|
# gemini: https://aistudio.google.com/app/apikey
|
|
# (GOOGLE_API_KEY is also accepted as an alias if GEMINI_API_KEY is unset)
|
|
GEMINI_API_KEY=
|
|
#GOOGLE_API_KEY=
|
|
|
|
# azure: Azure OpenAI (OpenAI-compatible). Use `--model azure:<deployment>`
|
|
# (the model name is your Azure *deployment* name).
|
|
#AZURE_OPENAI_API_KEY=
|
|
#AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com
|
|
#AZURE_OPENAI_API_VERSION=2024-10-21
|
|
|
|
# xai: https://console.x.ai/
|
|
XAI_API_KEY=
|
|
|
|
# nvidia_nim: https://build.nvidia.com/ (keys look like nvapi-...)
|
|
NVIDIA_NIM_API_KEY=
|
|
|
|
# deepseek: https://platform.deepseek.com/
|
|
DEEPSEEK_API_KEY=
|
|
|
|
# mistral: https://console.mistral.ai/
|
|
MISTRAL_API_KEY=
|
|
|
|
# qwen: https://dashscope-intl.aliyuncs.com/ (Alibaba DashScope)
|
|
DASHSCOPE_API_KEY=
|
|
|
|
# groq: https://console.groq.com/keys
|
|
GROQ_API_KEY=
|
|
|
|
# together: https://api.together.xyz/settings/api-keys
|
|
TOGETHER_API_KEY=
|
|
|
|
# openrouter: https://openrouter.ai/keys
|
|
OPENROUTER_API_KEY=
|
|
|
|
# opencode: https://opencode.ai/auth (OpenCode Zen gateway)
|
|
# Or skip the key entirely and use --subscription with the
|
|
# `opencode` CLI logged into your own Zen/plan account.
|
|
OPENCODE_API_KEY=
|
|
|
|
# nous: Nous Portal (https://portal.nousresearch.com) — Hermes models.
|
|
# Or skip the key entirely and use --subscription with the
|
|
# `hermes` CLI (`hermes setup --portal` for OAuth login).
|
|
NOUS_API_KEY=
|
|
|
|
# ollama: local, no key needed. Override the endpoint if not default:
|
|
#OLLAMA_BASE_URL=http://localhost:11434/v1
|
|
|
|
# litellm: point at your LiteLLM proxy (OpenAI-compatible). Route any
|
|
# model through it as `--model litellm:<model>`.
|
|
#LITELLM_BASE_URL=http://localhost:4000/v1
|
|
LITELLM_API_KEY=
|
|
|
|
# TypeSafe System One (RLCD — Reinforcement Learning for Calibrated Decisions).
|
|
# When set, NeuroSploit adjudicates each finding with a calibrated verdict
|
|
# (confirmed/needs-review/rejected) + an "impact demonstrated" judgment over the
|
|
# EVIDENCE, refining confidence and the needs-review boundary. Additive — never
|
|
# overrules a deterministic validator. Disable with NEUROSPLOIT_TYPESAFE=off.
|
|
TYPESAFE_API_KEY=
|