fix: add the missing provenance asset links to the reports

Signed-off-by: behnazh-w <[email protected]>

Author: behnazh-w

src/macaron/provenance/__init__.py

@@ -2,3 +2,16 @@
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/.
 
 """This package contains the provenance tools for software components."""
+
+from dataclasses import dataclass
+
+from macaron.slsa_analyzer.provenance.intoto import InTotoPayload
+
+
+@dataclass(frozen=True)
+class ProvenanceAsset:
+    """This class exists to hold a provenance payload with the original asset's name and URL."""
+
+    payload: InTotoPayload
+    name: str
+    url: str

src/macaron/provenance/provenance_finder.py

@@ -6,14 +6,14 @@
 import logging
 import os
 import tempfile
-from dataclasses import dataclass
 from functools import partial
 
 from packageurl import PackageURL
 from pydriller import Git
 
 from macaron.artifact.local_artifact import get_local_artifact_hash
 from macaron.config.defaults import defaults
+from macaron.provenance import ProvenanceAsset
 from macaron.repo_finder.commit_finder import AbstractPurlType, determine_abstract_purl_type
 from macaron.repo_finder.repo_finder_deps_dev import DepsDevRepoFinder
 from macaron.repo_finder.repo_utils import get_repo_tags
@@ -30,7 +30,6 @@
 )
 from macaron.slsa_analyzer.package_registry.npm_registry import NPMAttestationAsset
 from macaron.slsa_analyzer.package_registry.pypi_registry import find_or_create_pypi_asset
-from macaron.slsa_analyzer.provenance.intoto import InTotoPayload
 from macaron.slsa_analyzer.provenance.intoto.errors import LoadIntotoAttestationError
 from macaron.slsa_analyzer.provenance.loader import load_provenance_payload
 from macaron.slsa_analyzer.provenance.slsa import SLSAProvenanceData
@@ -41,15 +40,6 @@
 logger: logging.Logger = logging.getLogger(__name__)
 
 
-@dataclass(frozen=True)
-class ProvenanceAsset:
-    """This class exists to hold a provenance payload with the original asset's name and URL."""
-
-    payload: InTotoPayload
-    name: str
-    url: str
-
-
 class ProvenanceFinder:
     """This class is used to find and retrieve provenance files from supported registries."""
 

src/macaron/slsa_analyzer/analyzer.py

@@ -527,9 +527,10 @@ def run_single(
             # Try to discover GitHub attestation for the target software component.
             artifact_hash = get_artifact_hash(parsed_purl, local_artifact_dirs, package_registries_info)
             if artifact_hash:
-                provenance_payload = git_service.get_attestation_payload(
+                provenance_asset = git_service.get_attestation(
                     analyze_ctx.component.repository.full_name, artifact_hash
                 )
+                provenance_payload = provenance_asset.payload if provenance_asset else None
                 if provenance_payload:
                     try:
                         provenance_repo_url, provenance_commit_digest = extract_repo_and_commit_from_provenance(

src/macaron/slsa_analyzer/git_service/api_client.py

@@ -648,8 +648,8 @@ def download_asset(self, url: str, download_path: str) -> bool:
 
         return download_file_with_size_limit(url, headers, download_path, timeout, size_limit)
 
-    def get_attestation(self, full_name: str, artifact_hash: str) -> dict:
-        """Download and return the attestation associated with the passed artifact hash, if any.
+    def get_attestation(self, full_name: str, artifact_hash: str) -> tuple[str | None, dict]:
+        """Download and return the attestation url and content associated with the passed artifact hash, if any.
 
         Parameters
         ----------
@@ -660,12 +660,14 @@ def get_attestation(self, full_name: str, artifact_hash: str) -> dict:
 
         Returns
         -------
-        dict
-            The attestation data, or an empty dict if not found.
+        tuple[str|None,dict]
+            The attestation url and data, or None and an empty dict if not found.
         """
         url = f"{GhAPIClient._REPO_END_POINT}/{full_name}/attestations/sha256:{artifact_hash}"
         response_data = send_get_http(url, self.headers)
-        return response_data or {}
+        if not response_data:
+            return (None, {})
+        return (url, response_data)
 
 
 def get_default_gh_client(access_token: str) -> GhAPIClient:

src/macaron/slsa_analyzer/git_service/github.py

@@ -9,10 +9,11 @@
 from macaron.config.global_config import global_config
 from macaron.errors import ConfigurationError, RepoCheckOutError
 from macaron.json_tools import json_extract
+from macaron.provenance import ProvenanceAsset
 from macaron.slsa_analyzer import git_url
 from macaron.slsa_analyzer.git_service.api_client import GhAPIClient, get_default_gh_client
 from macaron.slsa_analyzer.git_service.base_git_service import BaseGitService
-from macaron.slsa_analyzer.provenance.intoto import InTotoPayload, ValidateInTotoPayloadError, validate_intoto_payload
+from macaron.slsa_analyzer.provenance.intoto import ValidateInTotoPayloadError, validate_intoto_payload
 from macaron.slsa_analyzer.provenance.loader import decode_provenance
 
 logger: logging.Logger = logging.getLogger(__name__)
@@ -96,7 +97,7 @@ def check_out_repo(self, git_obj: Git, branch: str, digest: str, offline_mode: b
 
         return git_obj
 
-    def get_attestation_payload(self, repository_name: str, artifact_hash: str) -> InTotoPayload | None:
+    def get_attestation(self, repository_name: str, artifact_hash: str) -> ProvenanceAsset | None:
         """Get the GitHub attestation associated with the given PURL, or None if it cannot be found.
 
         The schema of GitHub attestation can be found on the API page:
@@ -111,22 +112,26 @@ def get_attestation_payload(self, repository_name: str, artifact_hash: str) -> I
 
         Returns
         -------
-        InTotoPayload | None
-            The attestation payload, if found.
+        ProvenanceAsset | None
+            The provenance asset, if found.
         """
-        git_attestation_dict = self.api_client.get_attestation(repository_name, artifact_hash)
+        attestation_url, git_attestation_dict = self.api_client.get_attestation(repository_name, artifact_hash)
 
-        if not git_attestation_dict:
+        if not attestation_url or not git_attestation_dict:
             return None
 
         git_attestation_list = json_extract(git_attestation_dict, ["attestations"], list)
         if not git_attestation_list:
             return None
 
         payload = decode_provenance(git_attestation_list[0])
-
+        validated_payload = None
         try:
-            return validate_intoto_payload(payload)
+            validated_payload = validate_intoto_payload(payload)
         except ValidateInTotoPayloadError as error:
             logger.debug("Invalid attestation payload: %s", error)
             return None
+        if not validated_payload:
+            return None
+
+        return ProvenanceAsset(validated_payload, artifact_hash, attestation_url)