Files
t3mp3st/scripts/doctor.mjs
T
t3mp3st contributorsandClaude Opus 4.8 06ffe3ef66 feat: pack-hunt safety + opt-in Kali+ arsenal + capability-approval gate + tester-feedback UX
Adds three coordinated capabilities and tightens two defaults on purpose — this is
safety hardening, NOT a backward-compatible drop-in (see "Tightened defaults").
Fifteen independent adversarial review passes; findings fixed and test-pinned.

- Pack-hunt safety: a strict-majority adjudicator with a comment/string/regex/
  raw-string/heredoc/POD-aware cite-check (language-gated across C/C++/Py/Rust/Go/
  Java/JS/TS/shell/SQL/PHP/Ruby/Perl) so a hallucinated killing-guard can't refute
  a real finding — the cited comparison's operator must match source, and a
  string/regex/heredoc/generic-arglist/template-interpolation is blanked before
  matching. Plus a rate-limit/degraded-health tracker, a global LLM semaphore, and
  a PackBoard with an atomic claim CAS + snapshot-on-emit/clone-on-ingest.
- Opt-in Kali+ arsenal (T3MP3ST_FULL_ARSENAL, OFF by default): 35 default tools
  (31 built-in + 4 external-CLI wrappers) -> 83 with the catalog armed (verify-claims
  CLAIM 4). Most adapters need the underlying binary installed. metasploit / hydra /
  bloodhound are never minted through the generic factory.
- Capability-approval + spicy-action gate for the NEW dangerous arsenal only
  (pre-existing built-ins keep running freely): approve-once, fail-safe deny when
  unattended, redacted audit trail over SSE. T3MP3ST_GATE_BUILTINS=1 extends it to
  the spicy built-in probes. Audit redaction is a pure, unit-tested module.

Tightened defaults (intentional, ON by default — NOT backward-compatible):
- Egress containment: once a mission target is set, built-in networked tools refuse
  off-scope public hosts (not the target/subdomains, not loopback/private) with
  SCOPE DENIED — keeps the agent on authorized scope.
- Role-specialized operator toolkits: each archetype gets a curated default tool
  menu (scanner -> scan tools, exploiter -> sqli/xss/etc). Tools stay registered
  team-wide; the per-role menu is the operator's working set.

UX (from live-tester feedback): a one-click "Approve & run" modal when a standard
Hunt blocks on an external-target receipt (was a dead-end); bounded-parallel
benchmark file ingestion; the deterministic mission-gate chip co-located with the
subjective SITREP pace narration (no more "behind schedule" next to a clean gate);
and click-through finding detail + evidence in the UI (was export-only).

Docs: README + INTEGRITY_LEDGER made re-derivable — honest 35/83 tool count, the
egress-containment default documented, and the Cybench number reconciled to the
single verify-claims-enforced 23/40 = 58% (dropped the stale/uncited 21 and 26).
README voice pass: killed the underselling `Successful Exploits: 0` disqualifier
(read as "never popped anything" — false, given CVE-Zero + the live disclosure
pipeline); swagger now rests on receipts, not vibes. Also corrected the operator
status — the downstream operators run the SAME real tool-backed ReAct loop as
recon (not "orchestration stubs"); the honest limit is that the coordinated swarm
is unproven (single-agent is the benchmarked path), not that they're scaffolding.

Gates: 292 tests, tsc + lint clean, verify-claims 20/20, arsenal:smoke 125/0,
disclosure-CLI self-test 11/11.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-04 09:38:23 -04:00

165 lines
6.4 KiB
JavaScript

#!/usr/bin/env node
import { access, readFile } from 'node:fs/promises';
import { execFile } from 'node:child_process';
import { promisify } from 'node:util';
import process from 'node:process';
const execFileAsync = promisify(execFile);
const baseUrl = (process.env.T3MP3ST_API_URL || 'http://127.0.0.1:3333').replace(/\/$/, '');
const jsonMode = process.argv.includes('--json');
const strictMode = process.argv.includes('--strict');
const checks = [];
function check(name, passed, detail = '', severity = 'block') {
checks.push({ name, passed: Boolean(passed), detail, severity });
}
async function fileExists(path) {
try {
await access(path);
return true;
} catch {
return false;
}
}
async function commandPath(binary) {
try {
const { stdout } = await execFileAsync('which', [binary], { timeout: 1500 });
return stdout.trim();
} catch {
return '';
}
}
async function apiGet(path) {
const controller = new AbortController();
const timer = setTimeout(() => controller.abort(), 2500);
try {
const response = await fetch(`${baseUrl}${path}`, { signal: controller.signal });
const text = await response.text();
let data = {};
try {
data = text ? JSON.parse(text) : {};
} catch {
data = { raw: text };
}
return { ok: response.ok, status: response.status, data };
} finally {
clearTimeout(timer);
}
}
function scriptExists(pkg, scriptName) {
return Boolean(pkg.scripts && pkg.scripts[scriptName]);
}
async function main() {
const startedAt = new Date().toISOString();
const major = Number(process.versions.node.split('.')[0]);
check('Node runtime is supported', major >= 18, `node ${process.version}`);
const packageJsonExists = await fileExists('package.json');
check('package.json exists', packageJsonExists);
const pkg = packageJsonExists ? JSON.parse(await readFile('package.json', 'utf8')) : {};
for (const script of ['doctor', 'server', 'typecheck', 'test', 'arsenal:smoke', 'field:drill', 'exploit:smoke', 'prompt:audit']) {
check(`npm script: ${script}`, scriptExists(pkg, script), pkg.scripts?.[script] || 'missing');
}
const requiredFiles = [
'README.md',
'SECURITY.md',
'CONTRIBUTING.md',
'docs/index.html',
'docs/TEAM_PREVIEW.md',
'docs/ARSENAL_ACTIVATION_PLAN.md',
'docs/INSTALL_MATRIX.md',
'docs/SCOPE_AND_AUTHORIZATION.md',
'examples/demo-missions.json',
'src/server.ts',
'src/arsenal/catalog.ts',
];
for (const file of requiredFiles) {
check(`file: ${file}`, await fileExists(file), '', file.startsWith('docs/') || file.startsWith('examples/') ? 'warn' : 'block');
}
const commandChecks = [
['git', 'required for provenance'],
['node', 'required runtime'],
['npm', 'required package manager'],
['file', 'core evidence tool'],
['curl', 'core HTTP tool'],
['dig', 'DNS evidence tool'],
['whois', 'OSINT evidence tool'],
['nmap', 'optional high-value recon'],
['nuclei', 'optional high-value scanner'],
['semgrep', 'optional supply-chain scanner'],
['promptfoo', 'optional AI eval runner'],
];
for (const [binary, detail] of commandChecks) {
const path = await commandPath(binary);
const required = ['git', 'node', 'npm', 'file', 'curl'].includes(binary);
check(`command: ${binary}`, Boolean(path), path || `missing - ${detail}`, required ? 'block' : 'warn');
}
let apiReachable = false;
try {
const health = await apiGet('/health');
apiReachable = health.ok;
check('API health endpoint', health.ok && health.data.status === 'operational', `${health.status} ${health.data.status || 'unknown'}`);
if (health.ok) {
check('API exposes mission dispatch', health.data.missionDispatch === true, String(health.data.missionDispatch));
check('API exposes resources', Number(health.data.resources?.packs || 0) >= 10, `${health.data.resources?.packs || 0} packs`);
check('API exposes arsenal', Number(health.data.arsenal?.total || 0) >= 40, `${health.data.arsenal?.total || 0} adapters / ${health.data.arsenal?.commandReady || 0} command-ready`);
}
} catch (error) {
check('API health endpoint', false, `offline - run npm run server for live API checks (${error.name || 'error'})`, 'warn');
}
if (apiReachable) {
const preflight = await apiGet('/api/preflight');
check('Capability preflight', preflight.ok && typeof preflight.data.score === 'number', `${preflight.data.score ?? 'n/a'}/100`);
const arsenal = await apiGet('/api/arsenal/status');
check('Arsenal status', arsenal.ok && arsenal.data.schema_version === 't3mp3st.arsenal_status/v1', `${arsenal.data.summary?.installedCommandReady ?? 0}/${arsenal.data.summary?.commandReady ?? 0} installed`);
check('Arsenal does not fake empty coverage', arsenal.ok && arsenal.data.summary?.unmodeled === false, `unmodeled=${arsenal.data.summary?.unmodeled}`);
const activation = await apiGet('/api/arsenal/activation');
check('Arsenal activation plan', activation.ok && activation.data.schema_version === 't3mp3st.arsenal_activation/v1', `${activation.data.summary?.total || 0} wired / doc ${activation.data.localPlanDoc || 'missing'}`);
}
const blocks = checks.filter(item => !item.passed && item.severity === 'block');
const warnings = checks.filter(item => !item.passed && item.severity === 'warn');
const result = {
tool: 't3mp3st-doctor',
startedAt,
finishedAt: new Date().toISOString(),
baseUrl,
passed: blocks.length === 0 && (!strictMode || warnings.length === 0),
summary: {
checks: checks.length,
passed: checks.filter(item => item.passed).length,
warnings: warnings.length,
blockers: blocks.length,
strict: strictMode,
},
checks,
};
if (jsonMode) {
console.log(JSON.stringify(result, null, 2));
} else {
console.log(`T3MP3ST doctor: ${result.passed ? 'PASS' : 'CHECK REQUIRED'}`);
console.log(`${result.summary.passed}/${result.summary.checks} checks passed, ${result.summary.warnings} warning(s), ${result.summary.blockers} blocker(s)`);
for (const item of checks) {
const marker = item.passed ? 'ok' : item.severity === 'warn' ? 'warn' : 'block';
console.log(`- ${marker.padEnd(5)} ${item.name}${item.detail ? ` - ${item.detail}` : ''}`);
}
}
process.exitCode = result.passed ? 0 : 1;
}
main().catch(error => {
console.error(`doctor failed: ${error.stack || error.message || error}`);
process.exitCode = 1;
});