From e64cec5adda1276ab3e37359778ed352dae7fd7a Mon Sep 17 00:00:00 2001
From: yucheng-berri <yucheng@berri.ai>
Date: Thu, 25 Jun 2026 16:35:50 -0700
Subject: [PATCH] ci(image-scan): add Grype image scan for OS + library CVEs
 (#31151)

* ci(image-scan): add Grype image scan for OS + library CVEs

Builds each of the 6 Dockerfiles via a matrix and scans the resulting image
with Grype (pinned v0.114.0, sha256 verified), failing on fixable HIGH or
CRITICAL across both OS/apk and language packages. This catches the layer
osv-scan is structurally blind to (Wolfi/apk OS packages and vendored deps
like prisma's node engine), which is the structural reason the openssl CVE
slipped past CI and a customer's image scanner flagged it.

Skipped on fork PRs so an outside contributor cannot run arbitrary code on
our hosted runner via a malicious Dockerfile RUN line. The same pattern is
used by guard-fork-dependencies.yml.

Grype runs as a pinned binary with a verified checksum, so there is no
mutable-tag GitHub Action in the dependency chain and no vendor credentials
in the scan job. The job uses read-only contents permissions and an empty
top-level permissions block.

* ci(image-scan): scan only Dockerfile.non_root (rootless target)

All Dockerfile variants share the same wolfi base and apk set today, so a single scan of Dockerfile.non_root gives the same OS-layer coverage at one-sixth the build cost. Dockerfile.non_root is the rootless variant we ship (USER 65534), so the scan tracks the image customers actually run. Matrix-scan if the variants ever diverge.

* ci: retrigger checks (proxy_pass_through_endpoint_tests flaked on prior run)
---
 .github/workflows/image-scan.yml | 65 ++++++++++++++++++++++++++++++++
 1 file changed, 65 insertions(+)
 create mode 100644 .github/workflows/image-scan.yml

diff --git a/.github/workflows/image-scan.yml b/.github/workflows/image-scan.yml
new file mode 100644
index 00000000000..90ede5a653f
--- /dev/null
+++ b/.github/workflows/image-scan.yml
@@ -0,0 +1,65 @@
+name: Image Scan
+
+on:
+  pull_request:
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
+    paths:
+      - docker/Dockerfile.non_root
+      - uv.lock
+      - ui/litellm-dashboard/package-lock.json
+      - .github/workflows/image-scan.yml
+  schedule:
+    - cron: "41 6 * * *"
+  workflow_dispatch:
+
+permissions: {}
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  image-scan:
+    name: image-scan
+    runs-on: ubuntu-latest
+    if: >-
+      github.event_name != 'pull_request' ||
+      github.event.pull_request.head.repo.full_name == github.repository
+    timeout-minutes: 30
+    permissions:
+      contents: read
+    steps:
+      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
+
+      - name: Download Grype v0.114.0
+        run: |
+          curl -fsSL --retry 3 -o "$RUNNER_TEMP/grype.tar.gz" \
+            https://github.com/anchore/grype/releases/download/v0.114.0/grype_0.114.0_linux_amd64.tar.gz
+          echo "edda0968d8827daab01d32b3cd7de192ae0915005e7bbfcfef9e68e79bc43343  $RUNNER_TEMP/grype.tar.gz" | sha256sum -c -
+          tar xzf "$RUNNER_TEMP/grype.tar.gz" -C "$RUNNER_TEMP" grype
+          chmod +x "$RUNNER_TEMP/grype"
+
+      # Dockerfile.non_root is the rootless variant we ship. The other
+      # Dockerfiles share the same wolfi base and apk set, so OS-layer coverage
+      # is the same; matrix-scan if those variants ever diverge.
+      - name: Build runtime image
+        run: docker build -f docker/Dockerfile.non_root -t litellm-image-scan:${{ github.sha }} .
+
+      # Scans the whole shipped artifact: OS/apk plus every language package
+      # baked into the image, including ones no lockfile declares (e.g. prisma's
+      # vendored node engine) that osv-scan cannot see. osv-scan stays the fast
+      # source-level gate; this is the customer's-eye-view backstop. Credential-
+      # free OSS, run as a pinned, checksum-verified binary; no GitHub Action
+      # dependency and no vendor SaaS callout.
+      - name: Scan image for fixable HIGH/CRITICAL CVEs
+        run: |
+          "$RUNNER_TEMP/grype" litellm-image-scan:${{ github.sha }} \
+            --only-fixed \
+            --fail-on high \
+            --output table