fix(downloads): harden upload serving + ingest against stored-XSS and leaks (E7 review)
Deep-review remediation for the E7 upload path, all findings adversarially verified: - Serve every library file with a Content-Type chosen from the ffprobe-verified media_kind + a strict container allow-list (storage.served_media_type), never guessed from the user-controlled file extension. Closes a stored-XSS vector where a media/HTML polyglot uploaded as "evil.html" was served inline as text/html on the login-free /watch surface. Applied to both the authenticated /file and the public watch_file endpoints. - Classify uploaded still images (jpg/png/gif/webp/…) as media_kind='file' so they are force-downloaded and don't get a broken in-app video player. - Roll back the on-disk side of an upload when the ingest transaction fails after place_file (unlink the placed file + its deterministic poster path), so a failed commit can't orphan bytes in the GC-skipped .uploads tree. - Floor download_upload_max_bytes at min=1 so a stored 0 can't silently disable the per-file cap. - Dedupe the ffprobe-JSON invocation into edit.run_ffprobe_json (shared by probe_codecs and upload._probe) and the upload extension into storage._clean_upload_ext; drop the now-unused parse_probe_streams. Tests: public + authenticated force-download and the polyglot-not-served-as-HTML guard, the real _probe classifier (image/cover-art/dims/duration), the ingest rollback/cleanup path, the max_jobs branch, the cap-floor invariant, and run_ffprobe_json error handling.
This commit is contained in:
@@ -26,7 +26,6 @@ from app.db import get_db
|
||||
from app.downloads import credentials as dlcreds
|
||||
from app.downloads import edit as editmod
|
||||
from app.downloads import links as linksmod
|
||||
from app.downloads import mediakind
|
||||
from app.downloads import quota, service, storage
|
||||
from app.downloads import upload as uploadmod
|
||||
from app.models import (
|
||||
@@ -675,17 +674,21 @@ def download_file(
|
||||
|
||||
asset.last_access_at = datetime.now(timezone.utc)
|
||||
db.commit()
|
||||
# A generic uploaded file is served as a neutral, force-download attachment — never with a
|
||||
# sniffable content-type — so uploaded HTML/SVG can't execute inline on this origin. Media keeps
|
||||
# its guessed type so the in-app player streams it. Both are range-aware (FileResponse → 206).
|
||||
if asset.media_kind == mediakind.FILE:
|
||||
# The served Content-Type comes from the ffprobe-verified media_kind + a container allow-list
|
||||
# (storage.served_media_type), NEVER guessed from the file's own extension. A generic 'file' (and
|
||||
# any media whose container we don't recognise — e.g. a media/HTML polyglot named "evil.html")
|
||||
# returns None → a neutral force-download attachment, so uploaded HTML/SVG can't execute inline on
|
||||
# this origin. Recognised media is served with its real type so the in-app player streams it. Both
|
||||
# are range-aware (FileResponse → 206).
|
||||
media_type = storage.served_media_type(asset.media_kind, asset.container)
|
||||
if media_type is None:
|
||||
return FileResponse(
|
||||
path,
|
||||
filename=filename,
|
||||
media_type="application/octet-stream",
|
||||
content_disposition_type="attachment",
|
||||
)
|
||||
return FileResponse(path, filename=filename)
|
||||
return FileResponse(path, filename=filename, media_type=media_type)
|
||||
|
||||
|
||||
# --- editor filmstrip (scrub track) --------------------------------------------------------
|
||||
|
||||
@@ -15,7 +15,7 @@ from sqlalchemy.orm import Session
|
||||
from app.config import settings
|
||||
from app.db import get_db
|
||||
from app.downloads import links as linksmod
|
||||
from app.downloads import mediakind, storage
|
||||
from app.downloads import storage
|
||||
from app.models import DownloadJob, DownloadLink, MediaAsset
|
||||
from app.ratelimit import RateLimiter
|
||||
from app.security import verify_password
|
||||
@@ -122,11 +122,15 @@ def watch_file(token: str, g: str | None = None, db: Session = Depends(get_db)):
|
||||
raise HTTPException(status_code=404, detail="This video is no longer available.")
|
||||
|
||||
filename = storage.download_filename(asset.title or "video", asset.container, path)
|
||||
# A generic uploaded file (media_kind='file') is ALWAYS a force-download attachment with a
|
||||
# neutral type — never served inline — so arbitrary uploaded HTML/SVG can't execute on this
|
||||
# login-free public origin. Media follows the link's own inline/attachment choice so it can play
|
||||
# The served Content-Type comes from the asset's ffprobe-verified media_kind + a container
|
||||
# allow-list (storage.served_media_type) — NEVER guessed from the file's own extension. A generic
|
||||
# 'file' (and any media whose container we don't positively recognise, e.g. a media/HTML polyglot
|
||||
# named "evil.html") returns None → a neutral force-download attachment, so arbitrary uploaded
|
||||
# HTML/SVG can't execute inline on this login-free public origin. A recognised media container is
|
||||
# served with its real audio/video type, inline unless the link forces a download so it can play
|
||||
# in the watch page. Both are range-aware (FileResponse → 206) for seeking/resume.
|
||||
if asset.media_kind == mediakind.FILE:
|
||||
media_type = storage.served_media_type(asset.media_kind, asset.container)
|
||||
if media_type is None:
|
||||
return FileResponse(
|
||||
path,
|
||||
filename=filename,
|
||||
@@ -134,7 +138,9 @@ def watch_file(token: str, g: str | None = None, db: Session = Depends(get_db)):
|
||||
content_disposition_type="attachment",
|
||||
)
|
||||
disposition = "attachment" if link.allow_download else "inline"
|
||||
return FileResponse(path, filename=filename, content_disposition_type=disposition)
|
||||
return FileResponse(
|
||||
path, filename=filename, media_type=media_type, content_disposition_type=disposition
|
||||
)
|
||||
|
||||
|
||||
@router.get("/watch/{token}/poster.jpg")
|
||||
|
||||
Reference in New Issue
Block a user