fix(ci): stop checkov's suppressed checks from reopening as new alerts

Root cause found, not just worked around: checkov's SARIF exporter
includes every evaluated check as an ordinary result, including ones it
internally marked SKIPPED via the inline # checkov:skip= comments and
checkov.io/skipN annotations already on the Helm chart. It never uses
SARIF's own `suppressions` field and never drops them - so the exact same
already-suppressed finding reopens as a brand-new code scanning alert
number on every single run, forever (#6035/#6036, #6112-6115,
#6128-6131 are all the same 4 findings, manually dismissed 3 times now).

checkov's JSON output *does* correctly record which checks were skipped.
Added .github/scripts/filter_checkov_skipped.py, which cross-references
the JSON's skipped_checks against the SARIF's results (matched by check
ID + the last two path segments, since the two outputs use different path
roots) and drops anything checkov itself already decided to suppress,
before upload. Verified locally against a real checkov+helm run: removed
exactly the 4 known-suppressed helm chart results, left the 2 genuinely
real findings (deploy/gcp/cloudrun-service.yaml, deploy/kubernetes/
deployment.yaml) untouched.

.github/requirements/benchmark-extra.in

@@ -11,3 +11,4 @@ python-docx
 beautifulsoup4
 chardet
 langdetect
+en-core-web-sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.8.0/en_core_web_sm-3.8.0-py3-none-any.whl

.github/requirements/benchmark-extra.txt

@@ -408,6 +408,9 @@ cuda-toolkit==13.0.3.0 \
     # via
     #   -c requirements-ci.txt
     #   torch
+en-core-web-sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.8.0/en_core_web_sm-3.8.0-py3-none-any.whl \
+    --hash=sha256:1932429db727d4bff3deed6b34cfc05df17794f4a52eeb26cf8928f7c1a0fb85
+    # via -r .github/requirements/benchmark-extra.in
 et-xmlfile==2.0.0 \
     --hash=sha256:7a91720bc756843502c3b7504c77b8fe44217c85c537d85037f0f536151b2caa \
     --hash=sha256:dab3f4764309081ce75662649be815c4c9081e88f0837825f90fd28317d4da54

.github/scripts/filter_checkov_skipped.py

@@ -0,0 +1,76 @@
+"""Drop checkov-suppressed results from its SARIF output before upload.
+
+checkov's SARIF exporter includes every evaluated check as an ordinary
+result, including ones it internally marked SKIPPED via an inline
+`# checkov:skip=` comment or a `checkov.io/skipN` resource annotation - it
+never uses SARIF's `suppressions` field, and never drops them. checkov's
+JSON output *does* correctly record which checks were skipped, so this
+cross-references the two: any SARIF result whose (check_id, file) pair
+appears in the JSON's skipped_checks is removed before GitHub ever sees it.
+
+Without this, every already-suppressed finding reopens as a brand new code
+scanning alert on every run, forever (see #6035/#6036, #6112-6115,
+#6128-6131 for the pattern this was chasing before this script existed).
+
+Usage: filter_checkov_skipped.py <json_path> <sarif_in_path> <sarif_out_path>
+"""
+
+import json
+import sys
+
+
+def path_suffix(path: str, segments: int = 2) -> str:
+    """Last N path segments, normalized to forward slashes, lowercased.
+
+    checkov's JSON file_path and SARIF artifactLocation.uri are relative to
+    different roots (the scanned directory vs. a temp helm-render dir), so
+    they can't be compared directly - but the last couple of segments
+    (e.g. "templates/service.yaml") are stable across both and specific
+    enough in practice to avoid cross-file collisions.
+    """
+    normalized = path.replace("\\", "/").strip("/")
+    return "/".join(normalized.split("/")[-segments:]).lower()
+
+
+def main() -> None:
+    json_path, sarif_in_path, sarif_out_path = sys.argv[1:4]
+
+    with open(json_path, encoding="utf-8") as f:
+        checkov_json = json.load(f)
+    if isinstance(checkov_json, dict):
+        checkov_json = [checkov_json]
+
+    skipped = set()
+    for block in checkov_json:
+        for check in block.get("results", {}).get("skipped_checks", []):
+            skipped.add((check["check_id"], path_suffix(check["file_path"])))
+
+    with open(sarif_in_path, encoding="utf-8") as f:
+        sarif = json.load(f)
+
+    removed = 0
+    for run in sarif.get("runs", []):
+        kept = []
+        for result in run.get("results", []):
+            rule_id = result.get("ruleId")
+            locations = result.get("locations") or [{}]
+            uri = (
+                locations[0]
+                .get("physicalLocation", {})
+                .get("artifactLocation", {})
+                .get("uri", "")
+            )
+            if (rule_id, path_suffix(uri)) in skipped:
+                removed += 1
+                continue
+            kept.append(result)
+        run["results"] = kept
+
+    with open(sarif_out_path, "w", encoding="utf-8") as f:
+        json.dump(sarif, f)
+
+    print(f"Removed {removed} checkov-suppressed result(s) from the SARIF before upload.")
+
+
+if __name__ == "__main__":
+    main()

.github/workflows/benchmark.yml

@@ -44,12 +44,20 @@ jobs:
           pip install -r .github/requirements/pep517-build.txt --require-hashes
           pip install --no-deps --no-build-isolation -e .
           pip install -r .github/requirements/base-deps.txt --require-hashes
-          # NOTE: benchmarks/ does not currently exist in this repo, so this
-          # step and the run below it fail on any real invocation - pre-existing,
-          # unrelated to this pinning change. Left as-is since there's nothing
-          # to hash without knowing what belongs there.
-          pip install -r benchmarks/requirements.txt
-          python -m spacy download en_core_web_sm
+          # NOTE: benchmarks/ does not currently exist in this repo (neither
+          # requirements.txt nor benchmarks_runner.py below), so this job
+          # already fails on any real invocation - pre-existing, unrelated to
+          # this pinning change. The `pip install -r benchmarks/requirements.txt`
+          # step that used to be here is dropped rather than fixed: there's
+          # nothing to hash-pin without knowing what that file should
+          # contain, and an unpinned install here would just re-trip
+          # Scorecard's Pinned-Dependencies check for no real benefit, since
+          # the job can't run to completion regardless.
+          #
+          # `python -m spacy download en_core_web_sm` fetches an unpinned,
+          # unhashed wheel from spacy-models' GitHub releases - replaced with
+          # a hash-pinned direct-URL install of the same 3.8.0 model (matches
+          # the spacy==3.8.15 pinned in base-deps.txt) via benchmark-extra.txt.
           pip install -r .github/requirements/benchmark-extra.txt --require-hashes
 
       - name: Execute Benchmarks (Real Mode)

.github/workflows/defender-for-devops.yml

@@ -76,12 +76,28 @@ jobs:
         PYTHONUTF8: "1"
       run: |
         New-Item -ItemType Directory -Force reports | Out-Null
-        checkov --directory . --framework kubernetes helm dockerfile github_actions secrets bicep arm --soft-fail --output sarif --output-file-path reports/checkov.sarif
-        if (-not (Test-Path reports/checkov.sarif)) {
+        checkov --directory . --framework kubernetes helm dockerfile github_actions secrets bicep arm --soft-fail --output sarif --output json --output-file-path reports
+        if (-not (Test-Path reports/results_sarif.sarif)) {
           $sarif = Get-ChildItem -Path reports -Recurse -Filter *.sarif | Select-Object -First 1
           if ($null -eq $sarif) { throw "Checkov did not produce a SARIF file" }
-          Copy-Item $sarif.FullName reports/checkov.sarif
+          Copy-Item $sarif.FullName reports/results_sarif.sarif
         }
+        if (-not (Test-Path reports/results_json.json)) {
+          $json = Get-ChildItem -Path reports -Recurse -Filter *.json | Select-Object -First 1
+          if ($null -eq $json) { throw "Checkov did not produce a JSON file" }
+          Copy-Item $json.FullName reports/results_json.json
+        }
+
+    # checkov's SARIF exporter includes checks it internally marked SKIPPED
+    # (via the inline `# checkov:skip=` comments / `checkov.io/skipN`
+    # annotations already on the Helm chart) as ordinary un-suppressed
+    # results - it never uses SARIF's own `suppressions` field, so GitHub
+    # opens a fresh alert for the same already-suppressed finding on every
+    # single run (see #6035/#6036, #6112-6115, #6128-6131). checkov's JSON
+    # output does correctly record the skip, so cross-reference it here
+    # instead of re-dismissing the same alerts by hand forever.
+    - name: Filter checkov's own suppressed checks out of the SARIF
+      run: python .github/scripts/filter_checkov_skipped.py reports/results_json.json reports/results_sarif.sarif reports/checkov.sarif
 
     - name: Upload Checkov results to Security tab
       uses: github/codeql-action/upload-sarif@cdf488f595d80d6e07e03d4674febd5ab45fa938 # v4