Adds the --reach-use-only-pregenerated-sboms flag (#138)

* add flag --reach-use-only-pregenerated-sboms to exclude non-CDX and SPDX files from a Tier 1 reachability scan

* prepare for 2.2.44

* ensure only CDX/SPDX manifests and the .socket.facts.json are included in the final scan

* Moved the logic for find_sbom_files to find_files to avoid code duplication. Left the new function in place and just called find_files with the optional params

* Bumped minimum required SDK version with fix for no version in results

* bumped to fixed version of the SDK for no version in results

* Upgraded socketdev sdk in lock file

---------

Co-authored-by: Douglas Coburn <douglas@dactbc.com>

Author: mtorp

pyproject.toml

@@ -6,7 +6,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "socketsecurity"
-version = "2.2.43"
+version = "2.2.48"
 requires-python = ">= 3.10"
 license = {"file" = "LICENSE"}
 dependencies = [
@@ -16,7 +16,7 @@ dependencies = [
     'GitPython',
     'packaging',
     'python-dotenv',
-    'socketdev>=3.0.21,<4.0.0',
+    'socketdev>=3.0.22,<4.0.0',
     "bs4>=0.0.2",
 ]
 readme = "README.md"

socketsecurity/__init__.py

@@ -1,3 +1,3 @@
 __author__ = 'socket.dev'
-__version__ = '2.2.43'
+__version__ = '2.2.48'
 USER_AGENT = f'SocketPythonCLI/{__version__}'

socketsecurity/config.py

@@ -77,6 +77,7 @@ class CliConfig:
     reach_concurrency: Optional[int] = None
     reach_additional_params: Optional[List[str]] = None
     only_facts_file: bool = False
+    reach_use_only_pregenerated_sboms: bool = False
 
     @classmethod
     def from_args(cls, args_list: Optional[List[str]] = None) -> 'CliConfig':
@@ -139,6 +140,7 @@ def from_args(cls, args_list: Optional[List[str]] = None) -> 'CliConfig':
             'reach_concurrency': args.reach_concurrency,
             'reach_additional_params': args.reach_additional_params,
             'only_facts_file': args.only_facts_file,
+            'reach_use_only_pregenerated_sboms': args.reach_use_only_pregenerated_sboms,
             'version': __version__
         }
         try:
@@ -175,6 +177,11 @@ def from_args(cls, args_list: Optional[List[str]] = None) -> 'CliConfig':
             logging.error("--only-facts-file requires --reach to be specified")
             exit(1)
 
+        # Validate that reach_use_only_pregenerated_sboms requires reach
+        if args.reach_use_only_pregenerated_sboms and not args.reach:
+            logging.error("--reach-use-only-pregenerated-sboms requires --reach to be specified")
+            exit(1)
+
         # Validate reach_concurrency is >= 1 if provided
         if args.reach_concurrency is not None and args.reach_concurrency < 1:
             logging.error("--reach-concurrency must be >= 1")
@@ -602,6 +609,12 @@ def create_argument_parser() -> argparse.ArgumentParser:
         action="store_true",
         help="Submit only the .socket.facts.json file when creating full scan (requires --reach)"
     )
+    reachability_group.add_argument(
+        "--reach-use-only-pregenerated-sboms",
+        dest="reach_use_only_pregenerated_sboms",
+        action="store_true",
+        help="When using this option, the scan is created based only on pre-generated CDX and SPDX files in your project. (requires --reach)"
+    )
 
     parser.add_argument(
         '--version',

socketsecurity/core/__init__.py

@@ -281,12 +281,13 @@ def format_bytes(bytes_value):
         except Exception as e:
             log.error(f"Failed to save manifest tar.gz to {output_path}: {e}")
 
-    def find_files(self, path: str) -> List[str]:
+    def find_files(self, path: str, ecosystems: Optional[List[str]] = None) -> List[str]:
         """
         Finds supported manifest files in the given path.
 
         Args:
             path: Path to search for manifest files.
+            ecosystems: Optional list of ecosystems to include. If None, all ecosystems are included.
 
         Returns:
             List of found manifest file paths.
@@ -299,6 +300,9 @@ def find_files(self, path: str) -> List[str]:
         patterns = self.get_supported_patterns()
 
         for ecosystem in patterns:
+            # If ecosystems filter is provided, only include specified ecosystems
+            if ecosystems is not None and ecosystem not in ecosystems:
+                continue
             if ecosystem in self.config.excluded_ecosystems:
                 continue
             log.debug(f'Scanning ecosystem: {ecosystem}')
@@ -343,6 +347,23 @@ def find_files(self, path: str) -> List[str]:
 
         return file_list
 
+    def find_sbom_files(self, path: str) -> List[str]:
+        """
+        Finds only pre-generated SBOM files (CDX and SPDX) in the given path.
+
+        This is used with --reach-use-only-pregenerated-sboms to find only
+        pre-computed CycloneDX and SPDX manifest files.
+
+        Args:
+            path: Path to search for SBOM files.
+
+        Returns:
+            List of found CDX and SPDX file paths.
+        """
+        log.debug("Starting Find SBOM Files (CDX and SPDX only)")
+        sbom_ecosystems = ['cdx', 'spdx']
+        return self.find_files(path, ecosystems=sbom_ecosystems)
+
     def get_supported_patterns(self) -> Dict:
         """
         Gets supported file patterns from the Socket API.
@@ -547,7 +568,8 @@ def create_full_scan_with_report_url(
             no_change: bool = False,
             save_files_list_path: Optional[str] = None,
             save_manifest_tar_path: Optional[str] = None,
-            base_paths: Optional[List[str]] = None
+            base_paths: Optional[List[str]] = None,
+            explicit_files: Optional[List[str]] = None
     ) -> Diff:
         """Create a new full scan and return with html_report_url.
 
@@ -558,6 +580,7 @@ def create_full_scan_with_report_url(
             save_files_list_path: Optional path to save submitted files list for debugging
             save_manifest_tar_path: Optional path to save manifest files tar.gz archive
             base_paths: List of base paths for the scan (optional)
+            explicit_files: Optional list of explicit files to use instead of discovering files
 
         Returns:
             Dict with full scan data including html_report_url
@@ -571,11 +594,15 @@ def create_full_scan_with_report_url(
         if no_change:
             return diff
 
-        # Find manifest files from all paths
-        all_files = []
-        for path in paths:
-            files = self.find_files(path)
-            all_files.extend(files)
+        # Use explicit files if provided, otherwise find manifest files from all paths
+        if explicit_files is not None:
+            all_files = explicit_files
+            log.debug(f"Using {len(all_files)} explicit files instead of discovering files")
+        else:
+            all_files = []
+            for path in paths:
+                files = self.find_files(path)
+                all_files.extend(files)
 
         # Save submitted files list if requested
         if save_files_list_path and all_files:
@@ -943,7 +970,8 @@ def create_new_diff(
             no_change: bool = False,
             save_files_list_path: Optional[str] = None,
             save_manifest_tar_path: Optional[str] = None,
-            base_paths: Optional[List[str]] = None
+            base_paths: Optional[List[str]] = None,
+            explicit_files: Optional[List[str]] = None
     ) -> Diff:
         """Create a new diff using the Socket SDK.
 
@@ -954,16 +982,21 @@ def create_new_diff(
             save_files_list_path: Optional path to save submitted files list for debugging
             save_manifest_tar_path: Optional path to save manifest files tar.gz archive
             base_paths: List of base paths for the scan (optional)
+            explicit_files: Optional list of explicit files to use instead of discovering files
         """
         log.debug(f"starting create_new_diff with no_change: {no_change}")
         if no_change:
             return Diff(id="NO_DIFF_RAN", diff_url="", report_url="")
 
-        # Find manifest files from all paths
-        all_files = []
-        for path in paths:
-            files = self.find_files(path)
-            all_files.extend(files)
+        # Use explicit files if provided, otherwise find manifest files from all paths
+        if explicit_files is not None:
+            all_files = explicit_files
+            log.debug(f"Using {len(all_files)} explicit files instead of discovering files")
+        else:
+            all_files = []
+            for path in paths:
+                files = self.find_files(path)
+                all_files.extend(files)
 
         # Save submitted files list if requested
         if save_files_list_path and all_files:

socketsecurity/core/tools/reachability.py

@@ -101,10 +101,11 @@ def run_reachability_analysis(
         additional_params: Optional[List[str]] = None,
         allow_unverified: bool = False,
         enable_debug: bool = False,
+        use_only_pregenerated_sboms: bool = False,
     ) -> Dict[str, Any]:
         """
         Run reachability analysis.
-        
+
         Args:
             org_slug: Socket organization slug
             target_directory: Directory to analyze
@@ -125,7 +126,8 @@ def run_reachability_analysis(
             additional_params: Additional parameters to pass to coana CLI
             allow_unverified: Disable SSL certificate verification (sets NODE_TLS_REJECT_UNAUTHORIZED=0)
             enable_debug: Enable debug mode (passes -d flag to coana CLI)
-            
+            use_only_pregenerated_sboms: Use only pre-generated CDX and SPDX files for the scan
+
         Returns:
             Dict containing scan_id and report_path
         """
@@ -179,7 +181,10 @@ def run_reachability_analysis(
 
         if enable_debug:
             cmd.append("-d")
-        
+
+        if use_only_pregenerated_sboms:
+            cmd.append("--use-only-pregenerated-sboms")
+
         # Add any additional parameters provided by the user
         if additional_params:
             cmd.extend(additional_params)

socketsecurity/socketcli.py

@@ -167,6 +167,8 @@ def main_code():
 
     # Variable to track if we need to override files with facts file
     facts_file_to_submit = None
+    # Variable to track SBOM files to submit when using --reach-use-only-pregenerated-sboms
+    sbom_files_to_submit = None
 
     # Git setup
     is_repo = False
@@ -230,12 +232,14 @@ def main_code():
     # Run reachability analysis if enabled
     if config.reach:
         from socketsecurity.core.tools.reachability import ReachabilityAnalyzer
-        
+
         log.info("Starting reachability analysis...")
-        
+
         # Find manifest files in scan paths (excluding .socket.facts.json to avoid circular dependency)
         log.info("Finding manifest files for reachability analysis...")
         manifest_files = []
+
+        # Always find all manifest files for the tar hash upload
         for scan_path in scan_paths:
             scan_manifests = core.find_files(scan_path)
             # Filter out .socket.facts.json files from manifest upload
@@ -289,7 +293,8 @@ def main_code():
                     concurrency=config.reach_concurrency,
                     additional_params=config.reach_additional_params,
                     allow_unverified=config.allow_unverified,
-                    enable_debug=config.enable_debug
+                    enable_debug=config.enable_debug,
+                    use_only_pregenerated_sboms=config.reach_use_only_pregenerated_sboms
                 )
 
                 log.info(f"Reachability analysis completed successfully")
@@ -301,6 +306,17 @@ def main_code():
                 if config.only_facts_file:
                     facts_file_to_submit = os.path.abspath(output_path)
                     log.info(f"Only-facts-file mode: will submit only {facts_file_to_submit}")
+
+                # If reach-use-only-pregenerated-sboms mode, submit CDX, SPDX, and facts file
+                if config.reach_use_only_pregenerated_sboms:
+                    # Find only CDX and SPDX files for the final scan submission
+                    sbom_files_to_submit = []
+                    for scan_path in scan_paths:
+                        sbom_files_to_submit.extend(core.find_sbom_files(scan_path))
+                    # Use relative path for facts file
+                    if os.path.exists(output_path):
+                        sbom_files_to_submit.append(output_path)
+                    log.info(f"Pre-generated SBOMs mode: will submit {len(sbom_files_to_submit)} files (CDX, SPDX, and facts file)")
 
             except Exception as e:
                 log.error(f"Reachability analysis failed: {str(e)}")
@@ -331,6 +347,12 @@ def main_code():
         files_explicitly_specified = True
         log.debug(f"Overriding files to only submit facts file: {facts_file_to_submit}")
 
+    # Override files if reach-use-only-pregenerated-sboms mode is active
+    if sbom_files_to_submit:
+        specified_files = sbom_files_to_submit
+        files_explicitly_specified = True
+        log.debug(f"Overriding files to submit only SBOM files (CDX, SPDX, and facts): {sbom_files_to_submit}")
+
     # Determine files to check based on the new logic
     files_to_check = []
     force_api_mode = False
@@ -452,7 +474,7 @@ def main_code():
         log.info("Push initiated flow")
         if scm.check_event_type() == "diff":
             log.info("Starting comment logic for PR/MR event")
-            diff = core.create_new_diff(scan_paths, params, no_change=should_skip_scan, save_files_list_path=config.save_submitted_files_list, save_manifest_tar_path=config.save_manifest_tar, base_paths=base_paths)
+            diff = core.create_new_diff(scan_paths, params, no_change=should_skip_scan, save_files_list_path=config.save_submitted_files_list, save_manifest_tar_path=config.save_manifest_tar, base_paths=base_paths, explicit_files=sbom_files_to_submit)
             comments = scm.get_comments_for_pr()
             log.debug("Removing comment alerts")
 
@@ -505,14 +527,14 @@ def main_code():
             )
         else:
             log.info("Starting non-PR/MR flow")
-            diff = core.create_new_diff(scan_paths, params, no_change=should_skip_scan, save_files_list_path=config.save_submitted_files_list, save_manifest_tar_path=config.save_manifest_tar, base_paths=base_paths)
+            diff = core.create_new_diff(scan_paths, params, no_change=should_skip_scan, save_files_list_path=config.save_submitted_files_list, save_manifest_tar_path=config.save_manifest_tar, base_paths=base_paths, explicit_files=sbom_files_to_submit)
 
         output_handler.handle_output(diff)
-    
+
     elif config.enable_diff and not force_api_mode:
         # New logic: --enable-diff forces diff mode even with --integration api (no SCM)
         log.info("Diff mode enabled without SCM integration")
-        diff = core.create_new_diff(scan_paths, params, no_change=should_skip_scan, save_files_list_path=config.save_submitted_files_list, save_manifest_tar_path=config.save_manifest_tar, base_paths=base_paths)
+        diff = core.create_new_diff(scan_paths, params, no_change=should_skip_scan, save_files_list_path=config.save_submitted_files_list, save_manifest_tar_path=config.save_manifest_tar, base_paths=base_paths, explicit_files=sbom_files_to_submit)
         output_handler.handle_output(diff)
 
     elif config.enable_diff and force_api_mode:
@@ -530,12 +552,13 @@ def main_code():
             no_change=should_skip_scan,
             save_files_list_path=config.save_submitted_files_list,
             save_manifest_tar_path=config.save_manifest_tar,
-            base_paths=base_paths
+            base_paths=base_paths,
+            explicit_files=sbom_files_to_submit
         )
         log.info(f"Full scan created with ID: {diff.id}")
         log.info(f"Full scan report URL: {diff.report_url}")
         output_handler.handle_output(diff)
-    
+
     else:
         if force_api_mode:
             log.info("No Manifest files changed, creating Socket Report")
@@ -550,7 +573,8 @@ def main_code():
                 no_change=should_skip_scan,
                 save_files_list_path=config.save_submitted_files_list,
                 save_manifest_tar_path=config.save_manifest_tar,
-                base_paths=base_paths
+                base_paths=base_paths,
+                explicit_files=sbom_files_to_submit
             )
             log.info(f"Full scan created with ID: {diff.id}")
             log.info(f"Full scan report URL: {diff.report_url}")
@@ -561,7 +585,8 @@ def main_code():
                 no_change=should_skip_scan,
                 save_files_list_path=config.save_submitted_files_list,
                 save_manifest_tar_path=config.save_manifest_tar,
-                base_paths=base_paths
+                base_paths=base_paths,
+                explicit_files=sbom_files_to_submit
             )
             output_handler.handle_output(diff)