mirror of
https://github.com/yogeshojha/rengine.git
synced 2026-10-20 15:21:30 +02:00
Yogesh OjhaandClaude Opus 5
2375f1f1e4
The unit of exposure is now a service — (ip, port) — not a bare open port. Pipeline (EXPANSION): L0 produce hosts, L1 cdn_check + passive_ports, L2 port_scan, L3 http_probe, L4 screenshot/waf_detect/service_fingerprint. - cdn_check applies to every target type and records cdn_type, so a domain scan finally knows which addresses are CDN-fronted. cdn/waf is an edge you do not own (edge ports only); cloud is your own machine (scanned in full). - port_scan decides and records a per-address scan_policy (full/web/skip) honouring the scan context's excluded_ips, and offers port profiles, exclusions, scan type, a tarpit threshold and an address budget. - passive_ports reads Shodan internetdb through naabu -passive: keyless, touches_target=False, so a passive-intensity scan still gets exposure data. - http_probe seeds its host x port matrix from open ports and folds every live response back onto the port (is_http, tls, product). - service_fingerprint names the software behind non-web ports with a pure Python banner prober (tools/banner/), including a SOCKS5 CONNECT so it honours the context proxy. naabu -sV is unimplemented. - shared/definitions/ports.py is the one vocabulary; ip_inventory and port_inventory are the only writers of ip_addresses/ports. - open_ports_found is measured from the table (DERIVED_COUNTS): four stages write ports, so summing stage results double-counted. - naabu failures no longer report zero open ports as success. Surfaces: a Services tab (SERVICE_QUERY grammar, 16 fields, 18 counted leads, 9 group dimensions, detail sheet) built on the shared results shell, and an outlier-first Exposure panel on the Overview. Every count is a promise — leads, groups and panel pivots were verified to equal the row count they land on. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01BnC2xMMzV6WQnpDp5zcXoU
90 lines
2.9 KiB
Python
90 lines
2.9 KiB
Python
import uuid
|
|
from datetime import datetime
|
|
|
|
from pydantic import BaseModel
|
|
from sqlalchemy import Column
|
|
from sqlalchemy.types import JSON
|
|
from sqlmodel import Field, SQLModel, UniqueConstraint
|
|
|
|
from shared.utils.datetime import utc_now
|
|
|
|
|
|
class IpAddress(SQLModel, table=True):
|
|
__tablename__ = "ip_addresses"
|
|
__table_args__ = (UniqueConstraint("scan_id", "ip", name="uq_ipaddress_scan_ip"),)
|
|
|
|
id: uuid.UUID = Field(default_factory=uuid.uuid4, primary_key=True, index=True)
|
|
scan_id: uuid.UUID = Field(foreign_key="scans.id", index=True, ondelete="CASCADE")
|
|
target_id: uuid.UUID = Field(
|
|
foreign_key="targets.id", index=True, ondelete="CASCADE"
|
|
)
|
|
project_id: uuid.UUID = Field(foreign_key="projects.id", index=True)
|
|
|
|
ip: str = Field(max_length=45, index=True)
|
|
version: int = Field(default=4)
|
|
source: str = Field(max_length=30, index=True)
|
|
ptr_hostnames: list = Field(
|
|
default_factory=list, sa_column=Column(JSON, nullable=False)
|
|
)
|
|
asn: int | None = Field(default=None, index=True)
|
|
asn_org: str | None = Field(default=None, max_length=255)
|
|
prefix: str | None = Field(default=None, max_length=64)
|
|
country: str | None = Field(default=None, max_length=10)
|
|
is_cdn: bool = Field(default=False, index=True)
|
|
cdn_name: str | None = Field(default=None, max_length=100)
|
|
cdn_type: str | None = Field(default=None, max_length=20)
|
|
is_alive: bool | None = Field(default=None)
|
|
scan_policy: str | None = Field(default=None, max_length=16, index=True)
|
|
scan_policy_reason: str | None = Field(default=None, max_length=32)
|
|
|
|
discovered_at: datetime = Field(default_factory=utc_now)
|
|
created_at: datetime = Field(default_factory=utc_now)
|
|
|
|
|
|
class IpAddressRead(BaseModel):
|
|
id: uuid.UUID
|
|
scan_id: uuid.UUID
|
|
target_id: uuid.UUID
|
|
ip: str
|
|
version: int
|
|
source: str
|
|
ptr_hostnames: list[str] = Field(default_factory=list)
|
|
asn: int | None = None
|
|
asn_org: str | None = None
|
|
prefix: str | None = None
|
|
country: str | None = None
|
|
is_cdn: bool = False
|
|
cdn_name: str | None = None
|
|
cdn_type: str | None = None
|
|
is_alive: bool | None = None
|
|
scan_policy: str | None = None
|
|
scan_policy_reason: str | None = None
|
|
discovered_at: datetime
|
|
|
|
|
|
class IpAddressSummary(BaseModel):
|
|
total: int
|
|
alive: int
|
|
cdn: int
|
|
by_source: dict[str, int] = Field(default_factory=dict)
|
|
|
|
|
|
class TargetIpAddressRead(BaseModel):
|
|
ip: str
|
|
version: int
|
|
source: str
|
|
ptr_hostnames: list[str] = Field(default_factory=list)
|
|
asn: int | None = None
|
|
asn_org: str | None = None
|
|
prefix: str | None = None
|
|
country: str | None = None
|
|
is_cdn: bool = False
|
|
cdn_name: str | None = None
|
|
cdn_type: str | None = None
|
|
is_alive: bool | None = None
|
|
scan_policy: str | None = None
|
|
scan_count: int
|
|
last_scan_id: uuid.UUID
|
|
first_seen: datetime
|
|
last_seen: datetime
|