riposte-marketplace/integrations/rapid7-insightidr/scripts/search_investigation_alerts.py

import json, os, sys, urllib.request, urllib.parse, urllib.error

# The Alert Triage API lives under /idr/at, a base of its own — not /idr/v1 or
# /idr/v2 like the investigation endpoints. Same host, same API key.
AT = "idr/at/"


def _cfg():
    s = json.loads(os.environ.get("INTEGRATION_SECRETS", "{}"))
    region = str(s.get("region") or "us").strip().lower()
    base = "https://" + region + ".api.insight.rapid7.com/"
    headers = {"X-Api-Key": s.get("api_key", ""), "Content-Type": "application/json", "Accept": "application/json"}
    multi = str(s.get("is_multi_customer") or "").strip().lower() in ("1", "true", "yes")
    return base, headers, multi


def _inputs():
    return json.loads(os.environ.get("INTEGRATION_INPUTS", "{}"))


def _list(v):
    if v in (None, ""):
        return []
    if isinstance(v, list):
        return [str(x).strip() for x in v if str(x).strip()]
    return [p.strip() for p in str(v).split(",") if p.strip()]


def request(method, path, params=None, body=None):
    base, headers, _ = _cfg()
    url = base + path.lstrip("/")
    if params:
        clean = {k: v for k, v in params.items() if v not in (None, "")}
        if clean:
            url += ("&" if "?" in url else "?") + urllib.parse.urlencode(clean, doseq=True)
    data = json.dumps(body).encode("utf-8") if body is not None else None
    req = urllib.request.Request(url, data=data, headers=headers, method=method)
    with urllib.request.urlopen(req, timeout=90) as r:
        raw = r.read()
        return json.loads(raw) if raw else {}

import time
from datetime import datetime, timedelta, timezone

ISO = "%Y-%m-%dT%H:%M:%SZ"
# /alerts/ops/rrns takes a list; batching keeps one URL and one body reasonable.
RRN_BATCH = 100
# The server gives a command 90 seconds. Stop walking investigations well before
# that and report the truncation, rather than have the whole run killed and every
# alert in the window lost — a partial fetch that says so beats a silent zero.
DEFAULT_BUDGET_S = 60


def _alert_rrn(a):
    """The alert's RRN, or None when this alert has none.

    The investigation alert list is not consistent about where the RRN sits.
    Some entries carry it in `id` (rrn:alerts:eu:<org>:alert:1:<hex>); others put
    a plain UUID there and the RRN, if any, in `rrn`. `rrn` is therefore read
    first, and anything that is not RRN-shaped is dropped rather than sent on.

    That last part is not defensive habit. /alerts/ops/rrns validates the whole
    list and rejects the entire request when one entry is malformed, so a single
    UUID slipping through costs every alert in the batch — which is exactly how
    this failed: HTTP 400, eight invalid RRNs, zero alerts fetched, the whole run
    lost. Dropping them here means the investigation still arrives, with its
    unretrievable alerts counted rather than silently missing.
    """
    for v in (a.get("rrn"), a.get("id")):
        if isinstance(v, str) and v.startswith("rrn:"):
            return v
    return None


def run():
    _, _, multi = _cfg()
    inp = _inputs()
    limit = int(inp.get("limit") or 50)
    max_alerts = int(inp.get("max_alerts") or 500)
    budget = float(inp.get("time_budget_seconds") or DEFAULT_BUDGET_S)
    started = time.monotonic()

    start_time = inp.get("start_time")
    if not start_time:
        days = int(inp.get("default_days") or 1)
        start_time = (datetime.now(timezone.utc) - timedelta(days=days)).strftime(ISO)

    # 1) The investigations in the window. This is the unit that decides what is
    #    worth ingesting: an alert Rapid7 never folded into one is not returned by
    #    this command at all, which is the whole point of it.
    inv_page = request("GET", "idr/v2/investigations", params={
        "index": inp.get("index") or "0",
        "size": inp.get("page_size") or limit,
        "statuses": inp.get("statuses"),
        "priorities": inp.get("priorities"),
        "start_time": start_time,
        "end_time": inp.get("end_time"),
        "sort_field": "Created time",
        "sort_direction": "ASC",
        "multi-customer": "true" if multi else None,
    })
    investigations = (inv_page.get("data") or [])[:limit]

    # 2) Their alert RRNs. One call per investigation — there is no bulk form —
    #    so this is the step the time budget guards.
    order, by_rrn, truncated, skipped = [], {}, False, 0
    for inv in investigations:
        if time.monotonic() - started > budget or len(order) >= max_alerts:
            truncated = True
            break
        inv_rrn = inv.get("rrn") or ""
        if not inv_rrn:
            continue
        try:
            page = request("GET", "idr/v2/investigations/" + urllib.parse.quote(inv_rrn, safe="") + "/alerts",
                           params={"multi-customer": "true" if multi else None})
        except urllib.error.HTTPError:
            # One unreadable investigation must not cost the whole window. The
            # alert simply does not appear; the counts below say how many did.
            continue
        for a in (page.get("data") or []):
            rrn = _alert_rrn(a)
            if rrn is None:
                skipped += 1
                continue
            if rrn not in by_rrn:
                order.append(rrn)
                by_rrn[rrn] = inv
            if len(order) >= max_alerts:
                truncated = True
                break

    # 3) The alerts themselves, in batches. This is where the detection content
    #    lives — rule_keys_of_interest, mitre_tcodes, disposition — none of which
    #    the investigation or its alert list carries.
    field_ids = _list(inp.get("field_ids"))
    alerts = []
    for i in range(0, len(order), RRN_BATCH):
        batch = order[i:i + RRN_BATCH]
        body = {"rrns": batch}
        if field_ids:
            body["field_ids"] = field_ids
        out = request("POST", AT + "alerts/ops/rrns", body=body)
        alerts.extend(out.get("alerts") or [])

    # The investigation each alert came from, carried alongside so a mapper can
    # read the container's own title, priority and disposition without a second
    # feed. Alert fields are left untouched: `investigation_rrn` already exists
    # on the alert and nothing here may shadow it.
    if str(inp.get("include_investigation") or "true").strip().lower() in ("1", "true", "yes"):
        for a in alerts:
            inv = by_rrn.get(a.get("rrn"))
            if inv:
                a["investigation"] = inv

    print(json.dumps({
        "alerts": alerts,
        "metadata": {
            "investigations_read": len(investigations),
            "alert_rrns_collected": len(order),
            "alerts_returned": len(alerts),
            "alert_ids_without_rrn": skipped,
            "truncated": truncated,
            "elapsed_seconds": round(time.monotonic() - started, 1),
        },
    }))


try:
    run()
except urllib.error.HTTPError as e:
    detail = e.read().decode("utf-8", "replace")
    if e.code in (401, 403):
        detail += (" — the Alert Triage API (/idr/at) is only available to Managed Detection and"
                   " Response customers with access to the Alerts experience; a key that works on"
                   " the investigation endpoints can still be refused here")
    print(json.dumps({"error": "HTTP " + str(e.code), "detail": detail}))
    sys.exit(1)
except Exception as e:
    print(json.dumps({"error": str(e)}))
    sys.exit(1)