96f00c1c68
v3.4.1: CLI-only Rust harness — interactive wizard, smart selection, tool doctrine, Typst, status
...
- Remove Rust web server (axum/tower-http); CLI-only binary
- Verbose logging (-v) + unique run-id output folder runs/ns-<ts>-<target>/
- status.json lifecycle (running → complete) + ✓ COMPLETE summary
- Interactive wizard when run with no args; detailed --help with testphp/DVWA examples + Kali tip
- Tool-usage doctrine injected into recon/exploit prompts: curl + rustscan/nmap
(apt/brew/cargo install guidance) + browser via Playwright when present, else curl
- Smart recon-aware selection: map recon signals → agent categories, only run
matching agents; heuristic fallback when LLM selection is empty
- Cross-model false-positive validation: voting prefers a model other than the finder
- Playwright MCP auto-provision (npx) + per-backend support (claude/codex; gemini/grok degrade)
- Gemini provider (API + gemini CLI subscription)
- Typst report (report.typ + compiled report.pdf) via blank structured template
- Lenient finding parsing (confidence as word/number) — fixes empty-results bug
- bump version 3.4.0 -> 3.4.1
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-06-24 19:34:13 -03:00
e565270f43
fix: lenient finding parsing — models return confidence as words/strings
...
Root cause of empty results: models emit findings with confidence as a string
('High') or cvss as a number, but the Finding struct typed confidence as f64, so
serde failed the ENTIRE array on any mismatch -> 0 findings every run.
extract_findings now parses into serde_json::Value and coerces each field
(string/number/word), normalizes severity, and accepts qualitative confidence
(High->0.9 etc). Verified live: whitebox on a vulnerable sample now yields
validated findings (IDOR confirmed by vote).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-06-23 19:49:37 -03:00
c6fd5d6ac8
fix: resilient subscription CLI calls (retry, richer errors, capped concurrency)
...
The 'recon failed (claude subscription CLI failed: )' was a transient CLI failure
(rate limit / cold start) reported with a blank message and no retry.
- chat_cli: on non-zero exit, surface exit code + stdout (CLI writes the real
reason there, not stderr); treat empty output as an error
- pool.one(): retry up to 3x with backoff for transient failures (both
subscription and API paths)
- with_auth: cap concurrency to 3 on the subscription path — spawning many
parallel CLI processes itself trips provider rate limits
Verified: live subscription run recovers and completes recon → select → exploit
→ vote → artifacts.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-06-23 13:07:55 -03:00
3ca3f269ee
v3.4.x: intelligent agent selection, whitebox, recon/code agents, Gemini, artifacts, RL, XBOW GUI
...
Harness intelligence:
- After recon, the model SELECTS which specialist agents match the target
(select_agents) — runs the relevant subset, not blindly top-N
- RL reward store (rl.rs): per-agent weights persist to data/rl_state_rs.json,
reward validated findings (severity-weighted), decay idle, bias next run
- Run artifacts persisted as JSON + MD (recon, exploitation transcript,
findings, html report) under runs/<target>-<ts>/ for reuse by other AIs
Whitebox mode:
- run_whitebox: walks a repo, builds bounded source context, runs code agents,
validates by adversarial vote. CLI `whitebox <path>` + web "White-box" mode
Agents: +12 recon (subdomain/tech/js/api/secrets/dns/content/param/waf/cloud/
graphql/osint) and +24 code SAST reviewers (sqli/cmdi/path/ssrf/xss/deser/
secrets/crypto/authz/idor/xxe/redirect/ssti/race/eval/csrf/random/logging/
upload/mass-assign/jwt/cors). Loader gains recon/ + code/ categories → 249 total
Models: +Google Gemini provider (API + gemini CLI subscription); installed_cli_
backends now detects gemini; chat_cli handles gemini/codex/grok + optional
Playwright MCP (.mcp.json) on the subscription path with autonomy flags
GUI: full XBOW-style redesign — sidebar (Operate/Library), topbar status, mode
segment (black-box/white-box), model panel, live console, severity cards,
agent browser with category filters, models view; responsive + aligned
Verified: cargo build --release clean; CLI agents/whitebox; LIVE subscription
run shows model selecting 23→4 agents, RL update, artifacts written; GUI +
white-box toggle in Playwright.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-06-23 11:39:56 -03:00
d59f28f36d
v3.4.0: subscription backend (Claude Code / Codex / Grok logins)
...
The Rust harness can now use models two ways:
- API: provider API key (OpenAI-compatible HTTP) — existing path
- Subscription: drive the locally-installed agentic CLI login directly, no API
key (anthropic→claude, openai→codex, xai→grok)
- models.rs: ChatClient::chat_cli spawns the CLI (stdin prompt), cli_binary_for
+ installed_cli_backends + binary_in_path PATH detection
- pool.rs: ModelPool::with_auth(subscription); one() routes per model
- types/CLI: RunConfig.subscription + `run --subscription` flag
- web: /api/run honors "subscription"; /api/info reports detected cli_backends;
SPA gets a "Use subscription" toggle
Verified live: `run --subscription --model anthropic:claude-haiku-4-5` drove the
Claude subscription end-to-end (recon + agent + vote) with no API key set.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-06-22 16:59:35 -03:00
56d3f0c723
NeuroSploit v3.4.0 — Rust multi-model harness + Axum dashboard
...
New cargo workspace `neurosploit-rs/` (single `neurosploit` binary):
harness crate:
- models.rs: 11 OpenAI-compatible providers / 31 models (Claude, GPT, Grok,
NVIDIA NIM, DeepSeek, Mistral, Qwen, Groq, Together, OpenRouter, Ollama)
- pool.rs: ModelPool with bounded concurrency, provider failover, and N-model
validator voting (the panel doubles as the jury)
- agents.rs: loads the existing agents_md/ library (213 agents)
- pipeline.rs: recon → parallel exploit (semaphore-bounded) → N-model
adversarial vote → score; streams live progress over a channel
- report.rs: HTML report
- tokio + reqwest(rustls); offline mode runs the pipeline without API keys
app binary:
- clap CLI: serve | run | agents | models (run supports --model x N, --vote-n,
--max-agents, --offline)
- axum web dashboard with multi-model panel, live console, findings, agent
browser, embedded report; single binary serves the SPA (no npm/build)
Verified: cargo build clean; agents/models/offline-run CLI; server endpoints
(/api/info, /api/run lifecycle, /report); dashboard + live run in Playwright.
Docs: README v3.4.0 callout + RELEASE.md notes. target/ gitignored.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-06-21 19:58:43 -03:00
CyberSecurityUP