The Images page knew what was running and whether it was current. It could not say whether any of it was exploitable, which is the question people actually have about a homelab full of images they pulled once and forgot. Trivy runs as a throwaway container rather than being installed into StackPilot's image, reusing the helper-container pattern backups already use for volume contents. Three reasons: a 100 MB security tool and a vulnerability database that changes weekly have no business in a release artifact, pinning SCANNER_IMAGE is then a real version control, and the scanner updates itself by pulling a newer tag. It gets the socket read-only so it inspects images the daemon already has instead of pulling them again, and a named volume for its database so the ~50 MB download happens once rather than per scan. The number the UI leads with is "fixable", not the total. A base image with 300 unfixable low-severity CVEs is not a task and a page that shows 300 in red teaches people to ignore it; three findings with a fixed version available are something to do this afternoon. Counts are stored per severity, findings are sorted worst-first and capped at 200 — every finding is counted, only the list is trimmed, so the cap can never hide the severity distribution. The failure mode this had to avoid is a security feature that reads as clean when it is broken. A scanner that cannot run stores the error and *keeps the previous counts* rather than resetting to zero, so a transient daemon problem does not silently turn a bad image green. There is a test for exactly that, and another for unparseable output. Staleness is handled the same way: the local image id is recorded with the scan, and pulling the image marks the result stale instead of presenting yesterday's numbers for today's bytes. Sweeps are deliberately serial and singly-locked. Scanning is CPU- and IO-heavy, and running eight at once on a homelab box would starve the very containers the scan is meant to protect. docker-py is synchronous, so the scan itself goes to a thread — otherwise a ten-minute scan blocks every other request on the loop. Reading results is allowed for the read-only role, which the authorization matrix made me justify in writing: CVE ids and package versions for images whose tags and compose files that role can already see, and polling them is the monitoring use case a read-only API token exists for. Running a scan stays admin-only because it spends real CPU. 20 tests against a report shaped like Trivy's real output, covering the counting, the fixable number, worst-first ordering, the cap, both failure paths, staleness, and that two sweeps cannot overlap. Verified end to end through the API as well, including that a failed rescan keeps its previous counts and shows the error. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
152 lines
4.9 KiB
Python
152 lines
4.9 KiB
Python
"""Image listing, update checks and vulnerability scanning."""
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
|
|
from fastapi import APIRouter, Depends, HTTPException, Query, Request
|
|
from sqlmodel import Session
|
|
|
|
from auth import get_current_user, require_admin
|
|
from database import get_session
|
|
from models.image_scan import ImageScan, ScanDetail, ScanRequest, ScanSummary
|
|
from models.user import User
|
|
from services import audit_service, image_service, scan_service, update_service
|
|
|
|
router = APIRouter(prefix="/api/images", tags=["images"])
|
|
|
|
|
|
def _ip(request: Request) -> str:
|
|
return request.client.host if request.client else "unknown"
|
|
|
|
|
|
@router.get("")
|
|
def list_images(_user: User = Depends(get_current_user)) -> list[dict]:
|
|
return image_service.list_images()
|
|
|
|
|
|
@router.get("/updates")
|
|
def updates(_user: User = Depends(get_current_user)) -> dict:
|
|
return update_service.get_cache()
|
|
|
|
|
|
@router.post("/check")
|
|
async def check(_user: User = Depends(require_admin)) -> dict:
|
|
return await update_service.check_all()
|
|
|
|
|
|
@router.post("/prune")
|
|
def prune(
|
|
request: Request,
|
|
all_unused: bool = Query(False, alias="all"),
|
|
session: Session = Depends(get_session),
|
|
user: User = Depends(require_admin),
|
|
) -> dict:
|
|
result = image_service.prune_images(all_unused)
|
|
audit_service.record(
|
|
session, user=user.username, action="image.prune", target="*",
|
|
detail=f"all={all_unused} reclaimed={result.get('SpaceReclaimed')}",
|
|
ip=_ip(request),
|
|
)
|
|
return result
|
|
|
|
|
|
# --------------------------------------------------------------------------- #
|
|
# Vulnerability scanning
|
|
# --------------------------------------------------------------------------- #
|
|
|
|
|
|
def _summary(row: ImageScan, stale: bool = False) -> ScanSummary:
|
|
return ScanSummary(
|
|
image=row.image,
|
|
digest=row.digest,
|
|
scanner=row.scanner,
|
|
critical=row.critical,
|
|
high=row.high,
|
|
medium=row.medium,
|
|
low=row.low,
|
|
unknown=row.unknown,
|
|
fixable=row.fixable,
|
|
total=scan_service.total(row),
|
|
scanned_at=row.scanned_at,
|
|
duration_ms=row.duration_ms,
|
|
error=row.error,
|
|
stale=stale,
|
|
)
|
|
|
|
|
|
@router.get("/scans", response_model=list[ScanSummary])
|
|
def list_scans(
|
|
session: Session = Depends(get_session),
|
|
_user: User = Depends(get_current_user),
|
|
) -> list[ScanSummary]:
|
|
"""Every cached scan result. Cheap — no scanning happens here."""
|
|
rows = scan_service.all_scans(session).values()
|
|
return [_summary(row, scan_service.is_stale(row)) for row in rows]
|
|
|
|
|
|
@router.get("/scan", response_model=ScanDetail)
|
|
def scan_detail(
|
|
image: str = Query(...),
|
|
session: Session = Depends(get_session),
|
|
_user: User = Depends(get_current_user),
|
|
) -> ScanDetail:
|
|
row = scan_service.all_scans(session).get(image)
|
|
if not row:
|
|
raise HTTPException(status_code=404, detail=f"'{image}' has not been scanned")
|
|
try:
|
|
findings = json.loads(row.findings or "[]")
|
|
except json.JSONDecodeError:
|
|
findings = []
|
|
return ScanDetail(
|
|
**_summary(row, scan_service.is_stale(row)).model_dump(), findings=findings
|
|
)
|
|
|
|
|
|
@router.post("/scan", response_model=ScanSummary)
|
|
async def scan_image(
|
|
body: ScanRequest,
|
|
request: Request,
|
|
session: Session = Depends(get_session),
|
|
user: User = Depends(require_admin),
|
|
) -> ScanSummary:
|
|
"""Scan one image. Takes a while — the scanner runs as a container."""
|
|
image = (body.image or "").strip()
|
|
if not image:
|
|
raise HTTPException(status_code=400, detail="An image is required")
|
|
row = await scan_service.scan(session, image)
|
|
audit_service.record(
|
|
session, user=user.username, action="image.scan", target=image,
|
|
detail=row.error or f"{scan_service.total(row)} finding(s), {row.fixable} fixable",
|
|
ip=_ip(request),
|
|
)
|
|
if row.error:
|
|
# The row is stored either way, so the UI can show why it failed.
|
|
raise HTTPException(status_code=502, detail=row.error)
|
|
return _summary(row)
|
|
|
|
|
|
@router.post("/scan-all")
|
|
async def scan_all(
|
|
request: Request,
|
|
session: Session = Depends(get_session),
|
|
user: User = Depends(require_admin),
|
|
) -> dict:
|
|
"""Scan every image a stack is using. Serial, and one sweep at a time."""
|
|
images = sorted({row["tag"] for row in image_service.list_images() if row["stacks"]})
|
|
try:
|
|
result = await scan_service.sweep(session, images)
|
|
except scan_service.ScanError as exc:
|
|
raise HTTPException(status_code=409, detail=str(exc)) from exc
|
|
audit_service.record(
|
|
session, user=user.username, action="image.scan-all", target="*",
|
|
detail=f"{result['scanned']} scanned, {result['failed']} failed",
|
|
ip=_ip(request),
|
|
)
|
|
return result
|
|
|
|
|
|
@router.get("/scan-status")
|
|
def scan_status(_user: User = Depends(get_current_user)) -> dict:
|
|
"""Progress of a running sweep, so the button can show it."""
|
|
return scan_service.sweep_status()
|