feat: HF /scan endpoint (#2566)

* start by checking /scan during the checksum update

Signed-off-by: Dave Lee <dave@gray101.com>

* add back in golang side features: downloader/uri gets struct and scan function, gallery uses it, and secscan/models calls it.

Signed-off-by: Dave Lee <dave@gray101.com>

* add a param to scan specific urls - useful for debugging

Signed-off-by: Dave Lee <dave@gray101.com>

* helpful printouts

Signed-off-by: Dave Lee <dave@gray101.com>

* fix offsets

Signed-off-by: Dave Lee <dave@gray101.com>

* fix error and naming

Signed-off-by: Dave Lee <dave@gray101.com>

* expose error

Signed-off-by: Dave Lee <dave@gray101.com>

* fix json tags

Signed-off-by: Dave Lee <dave@gray101.com>

* slight wording change

Signed-off-by: Dave Lee <dave@gray101.com>

* go mod tidy - getting warnings

Signed-off-by: Dave Lee <dave@gray101.com>

* split out python to make editing easier, add some simple code  to delete contaminated entries from gallery

Signed-off-by: Dave Lee <dave@gray101.com>

* o7 to my favorite part of our old name, go-skynet

Signed-off-by: Dave Lee <dave@gray101.com>

* merge fix

Signed-off-by: Dave Lee <dave@gray101.com>

* merge fix

Signed-off-by: Dave Lee <dave@gray101.com>

* merge fix

Signed-off-by: Dave Lee <dave@gray101.com>

* address review comments

Signed-off-by: Dave Lee <dave@gray101.com>

* forgot secscan could accept multiple URL at once

Signed-off-by: Dave Lee <dave@gray101.com>

* invert naming and actually use it

Signed-off-by: Dave Lee <dave@gray101.com>

* missed cli/models.go

Signed-off-by: Dave Lee <dave@gray101.com>

* Update .github/check_and_update.py

Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Signed-off-by: Dave <dave@gray101.com>

---------

Signed-off-by: Dave Lee <dave@gray101.com>
Signed-off-by: Dave <dave@gray101.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
This commit is contained in:
Dave 2024-07-10 07:18:32 -04:00 committed by GitHub
parent cbb93bd8ec
commit 133987b1fb
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
15 changed files with 282 additions and 125 deletions

View file

@ -15,7 +15,7 @@ import (
)
// Installs a model from the gallery
func InstallModelFromGallery(galleries []config.Gallery, name string, basePath string, req GalleryModel, downloadStatus func(string, string, string, float64)) error {
func InstallModelFromGallery(galleries []config.Gallery, name string, basePath string, req GalleryModel, downloadStatus func(string, string, string, float64), enforceScan bool) error {
applyModel := func(model *GalleryModel) error {
name = strings.ReplaceAll(name, string(os.PathSeparator), "__")
@ -63,7 +63,7 @@ func InstallModelFromGallery(galleries []config.Gallery, name string, basePath s
return err
}
if err := InstallModel(basePath, installName, &config, model.Overrides, downloadStatus); err != nil {
if err := InstallModel(basePath, installName, &config, model.Overrides, downloadStatus, enforceScan); err != nil {
return err
}
@ -228,3 +228,29 @@ func DeleteModelFromSystem(basePath string, name string, additionalFiles []strin
return err
}
// This is ***NEVER*** going to be perfect or finished.
// This is a BEST EFFORT function to surface known-vulnerable models to users.
func SafetyScanGalleryModels(galleries []config.Gallery, basePath string) error {
galleryModels, err := AvailableGalleryModels(galleries, basePath)
if err != nil {
return err
}
for _, gM := range galleryModels {
if gM.Installed {
err = errors.Join(err, SafetyScanGalleryModel(gM))
}
}
return err
}
func SafetyScanGalleryModel(galleryModel *GalleryModel) error {
for _, file := range galleryModel.AdditionalFiles {
scanResults, err := downloader.HuggingFaceScan(file.URI)
if err != nil && !errors.Is(err, downloader.ErrNonHuggingFaceFile) {
log.Error().Str("model", galleryModel.Name).Strs("clamAV", scanResults.ClamAVInfectedFiles).Strs("pickles", scanResults.DangerousPickles).Msg("Contains unsafe file(s)!")
return err
}
}
return nil
}