Wraps the three remaining 🚧 items from the README so every collector the threat-model promises is actually live, and the Tier-4 path (real-malware fetch + upload + exec) works end-to-end as soon as a sha256 lands in samples/store/. Closes spectral/CIS490#4, #5, #6. == #6 — Bridge pcap wiring == EpisodeConfig grows three optional fields: bridge_iface: str | None # e.g. "br-malware" bridge_ip: str = "10.200.0.1" pcap_snaplen: int = 256 When bridge_iface is set, EpisodeRunner spawns tcpdump for the duration of the schedule (network.pcap), stops it cleanly on episode end, and runs collectors.pcap.bucketize() to produce netflow.jsonl per the 100-ms schema in docs/data-model.md. EpisodeResult + meta.result gain rows_netflow + pcap_bytes counters. vm/launch_demo.sh + launch_target.sh now switch between SLIRP usermode and tap+bridge based on $BRIDGE — operator pre-creates the tap as a bridge member, no sudo from the launcher. run_real_vm_demo.py picks BRIDGE up from env so the fleet runner can opt entire waves into pcap mode by exporting BRIDGE before invocation. == #5 — Source 3 perf collector == collectors/perf_qemu.py shells out to ``perf stat -p <pid> -I 100 -j`` and parses the per-event JSON stream. Aggregates one row per interval across the canonical event set (cycles/instructions/cache-{refs,misses}/ branches/branch-misses/page-faults/context-switches), computes IPC + cache-miss rate. Tolerates missing events (``<not counted>`` / ``<not supported>``) without dropping the row, and skips cleanly when ``perf`` isn't on PATH or the process can't be attached. EpisodeConfig.enable_perf=True opts into the collector — off by default because perf needs CAP_SYS_ADMIN or perf_event_paranoid <= 1. When enabled, runs as a parallel thread alongside the other collectors; EpisodeResult.rows_perf records the count. == #4 — Tier 4 (real-malware fetch + upload + exec) == tools/fetch_sample.py: pulls a sample by sha256 from MalwareBazaar (API key from env or samples/.bazaar.token), unzips with the standard "infected" password, verifies the resulting binary's sha256, lands at samples/store/<sha256>. Idempotent — already-staged correct binaries return immediately. samples/manifest.py: Sample.binary_path(store_root) resolves to the staged binary path, or None for mimics / not-yet-fetched real samples. exploits/workloads.py: real_binary_workload(bytes, sample) builds a Workload that base64-uploads the binary into the shell session via a heredoc, decodes + chmods + execs it in the background, captures the PID for clean stop on dormant. Per-profile pid/bin paths so concurrent samples in the same guest don't collide. exploits/driver.py: dispatch order is now: 1) sample.kind == "real" + binary staged at sample_store_root → real_binary_workload (Tier 4) 2) profile mimic from workloads.workload_for() (Tier 3 v2) 3) None → driver v1 fallback yes-loop DriverConfig.sample_store_root is the new field; run_tier3_demo.py wires it to repo_root/samples/store. driver_setup event records sample_sha256 so trainers can join Tier-4 episodes against the manifest by hash. samples/store/.gitkeep added (binaries themselves are gitignored). Tests: 102 pass (was 86). New suites: tests/test_perf_qemu.py — parser + builder + perf-missing fallback tests/test_tier4.py — real_binary_workload base64 round-trip, stop-cmd kills pidfile, per-profile path isolation, driver dispatch chooses real vs mimic correctly, fetcher input validation and cached-fast-path Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
266 lines
8.7 KiB
Python
266 lines
8.7 KiB
Python
"""Tier-3: real VM, real exploit, honest ``armed -> infecting`` transition.
|
|
|
|
Boots the vulnerable target VM, drives an msfrpcd-fired exploit module
|
|
against it, and lets the orchestrator's host /proc collector sample
|
|
the qemu-system pid throughout. Compared to ``run_real_vm_demo.py``:
|
|
the workload that crosses the ``armed -> infecting`` boundary is now
|
|
generated by an actual exploit landing a session, not by a script in
|
|
the guest.
|
|
|
|
Prereqs:
|
|
- vm/images/<target>.qcow2 (e.g. Metasploitable2)
|
|
- msfrpcd running locally:
|
|
msfrpcd -P <password> -U msf -a 127.0.0.1 -p 55553
|
|
- ``msgpack`` python package installed (added to runtime deps)
|
|
|
|
Run:
|
|
MSFRPC_PASSWORD=<pass> uv run python tools/run_tier3_demo.py \\
|
|
--module vsftpd_234_backdoor \\
|
|
--data-root data
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
import logging
|
|
import os
|
|
import signal
|
|
import subprocess
|
|
import sys
|
|
import time
|
|
from pathlib import Path
|
|
|
|
# Allow running as a script.
|
|
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
|
|
|
|
from exploits.driver import DriverConfig, MSFExploitDriver # noqa: E402
|
|
from exploits.modules import load_module_config # noqa: E402
|
|
from exploits.msfrpc import MSFRpcClient, MSFRpcConfig # noqa: E402
|
|
from orchestrator.episode import EpisodeConfig, EpisodeRunner # noqa: E402
|
|
from samples.manifest import SampleManifest # noqa: E402
|
|
|
|
|
|
# Same envelope shape as Tier 2 so plots are comparable. Slightly more
|
|
# armed/infecting time because real exploit fire + session establishment
|
|
# takes hundreds of ms to a few seconds.
|
|
DEFAULT_SCHEDULE = [
|
|
("clean", 10.0),
|
|
("armed", 3.0),
|
|
("infecting", 5.0),
|
|
("infected_running", 25.0),
|
|
("dormant", 15.0),
|
|
("infected_running", 20.0),
|
|
("dormant", 5.0),
|
|
("clean", 5.0),
|
|
]
|
|
|
|
|
|
def _wait_for_path(path: Path, timeout_s: float) -> None:
|
|
deadline = time.monotonic() + timeout_s
|
|
while time.monotonic() < deadline:
|
|
if path.exists() and path.read_text().strip():
|
|
return
|
|
time.sleep(0.2)
|
|
raise TimeoutError(f"{path} never appeared within {timeout_s}s")
|
|
|
|
|
|
def _wait_for_tcp(host: str, port: int, timeout_s: float) -> None:
|
|
import socket
|
|
deadline = time.monotonic() + timeout_s
|
|
last_err: Exception | None = None
|
|
while time.monotonic() < deadline:
|
|
try:
|
|
with socket.create_connection((host, port), timeout=1.0):
|
|
return
|
|
except OSError as e:
|
|
last_err = e
|
|
time.sleep(1.0)
|
|
raise TimeoutError(
|
|
f"target service {host}:{port} not reachable within {timeout_s}s "
|
|
f"(last: {last_err})"
|
|
)
|
|
|
|
|
|
def main() -> int:
|
|
parser = argparse.ArgumentParser(prog="run_tier3_demo")
|
|
parser.add_argument("--data-root", default="data")
|
|
parser.add_argument("--interval-ms", type=int, default=100)
|
|
parser.add_argument(
|
|
"--module",
|
|
default="vsftpd_234_backdoor",
|
|
help="Module config name in exploits/modules/<name>.toml",
|
|
)
|
|
parser.add_argument(
|
|
"--target-ip",
|
|
default="127.0.0.1",
|
|
help="Address the exploit module sets RHOSTS to. With the SLIRP "
|
|
"launcher (default), the guest's vulnerable port is hostfwd'd to "
|
|
"loopback; on a host-only bridge, this is the guest's bridge IP.",
|
|
)
|
|
parser.add_argument(
|
|
"--target-port",
|
|
type=int,
|
|
default=21,
|
|
help="Probe port to wait on before firing the exploit",
|
|
)
|
|
parser.add_argument(
|
|
"--run-dir",
|
|
default="/tmp/cis490-target",
|
|
help="QEMU run dir (sockets + pidfile)",
|
|
)
|
|
parser.add_argument(
|
|
"--msfrpc-host", default=os.environ.get("MSFRPC_HOST", "127.0.0.1"),
|
|
)
|
|
parser.add_argument(
|
|
"--msfrpc-port", type=int,
|
|
default=int(os.environ.get("MSFRPC_PORT", "55553")),
|
|
)
|
|
parser.add_argument(
|
|
"--msfrpc-user", default=os.environ.get("MSFRPC_USER", "msf"),
|
|
)
|
|
parser.add_argument(
|
|
"--keep-vm",
|
|
action="store_true",
|
|
help="leave the VM running after the episode finishes",
|
|
)
|
|
parser.add_argument(
|
|
"--target-boot-timeout",
|
|
type=float,
|
|
default=180.0,
|
|
help="how long to wait for the guest's vulnerable service to listen",
|
|
)
|
|
parser.add_argument(
|
|
"--sample",
|
|
default=os.environ.get("SAMPLE_NAME"),
|
|
help="Pick a workload profile from the manifest by name. Fleet runner "
|
|
"passes this via SAMPLE_NAME env. Without it, falls back to the v1 yes-loop.",
|
|
)
|
|
parser.add_argument(
|
|
"--manifest",
|
|
default=str(Path(__file__).resolve().parent.parent / "samples" / "manifest.toml"),
|
|
)
|
|
args = parser.parse_args()
|
|
|
|
logging.basicConfig(
|
|
level=logging.INFO,
|
|
format="%(asctime)s %(levelname)s %(name)s %(message)s",
|
|
)
|
|
log = logging.getLogger("cis490.run_tier3_demo")
|
|
|
|
msfrpc_password = os.environ.get("MSFRPC_PASSWORD")
|
|
if not msfrpc_password:
|
|
log.error("MSFRPC_PASSWORD env var must be set")
|
|
return 2
|
|
|
|
repo_root = Path(__file__).resolve().parent.parent
|
|
launcher = repo_root / "vm" / "launch_target.sh"
|
|
modules_dir = repo_root / "exploits" / "modules"
|
|
module_path = modules_dir / f"{args.module}.toml"
|
|
if not module_path.exists():
|
|
log.error("no module config at %s", module_path)
|
|
return 2
|
|
|
|
module = load_module_config(module_path)
|
|
log.info("module loaded: %s (%s)", module.name, module.module_path)
|
|
|
|
sample = None
|
|
if args.sample:
|
|
manifest = SampleManifest.load(args.manifest)
|
|
sample = next((s for s in manifest.samples if s.name == args.sample), None)
|
|
if sample is None:
|
|
log.error("sample %r not in manifest %s", args.sample, args.manifest)
|
|
return 2
|
|
log.info("sample=%s profile=%s kind=%s",
|
|
sample.name, sample.profile, sample.kind)
|
|
|
|
run_dir = Path(args.run_dir)
|
|
if run_dir.exists():
|
|
import shutil
|
|
shutil.rmtree(run_dir)
|
|
run_dir.mkdir(parents=True, exist_ok=True)
|
|
pid_file = run_dir / "qemu.pid"
|
|
|
|
log.info("booting target VM via %s (RUN_DIR=%s)", launcher, run_dir)
|
|
env = os.environ.copy()
|
|
env["RUN_DIR"] = str(run_dir)
|
|
qemu = subprocess.Popen(
|
|
[str(launcher)],
|
|
cwd=str(repo_root),
|
|
env=env,
|
|
stdout=subprocess.DEVNULL,
|
|
stderr=subprocess.DEVNULL,
|
|
start_new_session=True,
|
|
)
|
|
|
|
try:
|
|
_wait_for_path(pid_file, timeout_s=15.0)
|
|
qemu_pid = int(pid_file.read_text().strip())
|
|
log.info("qemu pid = %d; waiting for service on %s:%d (timeout %.0fs)",
|
|
qemu_pid, args.target_ip, args.target_port,
|
|
args.target_boot_timeout)
|
|
_wait_for_tcp(args.target_ip, args.target_port, args.target_boot_timeout)
|
|
log.info("target service is up")
|
|
|
|
client = MSFRpcClient(
|
|
MSFRpcConfig(
|
|
host=args.msfrpc_host,
|
|
port=args.msfrpc_port,
|
|
user=args.msfrpc_user,
|
|
password=msfrpc_password,
|
|
)
|
|
)
|
|
|
|
cfg = EpisodeConfig(
|
|
target_pid=qemu_pid,
|
|
duration_s=sum(d for _, d in DEFAULT_SCHEDULE),
|
|
interval_ms=args.interval_ms,
|
|
data_root=Path(args.data_root),
|
|
phase_schedule=DEFAULT_SCHEDULE,
|
|
image_name=module.name + "-target",
|
|
snapshot_name="qcow2-snapshot-on",
|
|
)
|
|
runner = EpisodeRunner(cfg)
|
|
|
|
driver = MSFExploitDriver(
|
|
client=client,
|
|
module=module,
|
|
cfg=DriverConfig(
|
|
target_ip=args.target_ip,
|
|
sample_store_root=repo_root / "samples" / "store",
|
|
),
|
|
emit_event=runner.emit_event,
|
|
sample=sample,
|
|
)
|
|
runner.on_phase = driver.set_phase
|
|
|
|
driver.setup()
|
|
try:
|
|
result = runner.run()
|
|
finally:
|
|
driver.teardown()
|
|
|
|
print()
|
|
print(f"episode_id = {result.episode_id}")
|
|
print(f"path = {result.episode_dir}")
|
|
print(f"rows_proc = {result.rows_proc}")
|
|
print(f"phases = {result.phases_observed}")
|
|
print(f"module = {module.module_path}")
|
|
print()
|
|
print("To plot:")
|
|
print(f" uv run python tools/plot_envelope.py {result.episode_dir}")
|
|
return 0
|
|
finally:
|
|
if not args.keep_vm:
|
|
log.info("shutting down VM (pid=%d)", qemu.pid)
|
|
try:
|
|
os.killpg(os.getpgid(qemu.pid), signal.SIGTERM)
|
|
except ProcessLookupError:
|
|
pass
|
|
try:
|
|
qemu.wait(timeout=5)
|
|
except subprocess.TimeoutExpired:
|
|
os.killpg(os.getpgid(qemu.pid), signal.SIGKILL)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main())
|