cartography 0.94.0rc2__py3-none-any.whl → 0.95.0__py3-none-any.whl

cartography/intel/semgrep/dependencies.py

@@ -0,0 +1,201 @@
+import logging
+from typing import Any
+from typing import Callable
+from typing import Dict
+from typing import List
+
+import neo4j
+import requests
+from requests.exceptions import HTTPError
+from requests.exceptions import ReadTimeout
+
+from cartography.client.core.tx import load
+from cartography.graph.job import GraphJob
+from cartography.models.semgrep.dependencies import SemgrepGoLibrarySchema
+from cartography.stats import get_stats_client
+from cartography.util import merge_module_sync_metadata
+from cartography.util import timeit
+
+logger = logging.getLogger(__name__)
+stat_handler = get_stats_client(__name__)
+_PAGE_SIZE = 10000
+_TIMEOUT = (60, 60)
+_MAX_RETRIES = 3
+
+
+@timeit
+def get_dependencies(semgrep_app_token: str, deployment_id: str, ecosystems: List[str]) -> List[Dict[str, Any]]:
+    """
+    Gets all dependencies for the given ecosystems within the given Semgrep deployment ID.
+    param: semgrep_app_token: The Semgrep App token to use for authentication.
+    param: deployment_id: The Semgrep deployment ID to use for retrieving dependencies.
+    param: ecosystems: One or more ecosystems to import dependencies from, e.g. "gomod" or "pypi".
+    The list of supported ecosystems is defined here:
+    https://semgrep.dev/api/v1/docs/#tag/SupplyChainService/operation/semgrep_app.products.sca.handlers.dependency.list_dependencies_conexxion
+    """
+    all_deps = []
+    deps_url = f"https://semgrep.dev/api/v1/deployments/{deployment_id}/dependencies"
+    has_more = True
+    page = 0
+    retries = 0
+    headers = {
+        "Content-Type": "application/json",
+        "Authorization": f"Bearer {semgrep_app_token}",
+    }
+
+    request_data: dict[str, Any] = {
+        "pageSize": _PAGE_SIZE,
+        "dependencyFilter": {
+            "ecosystem": ecosystems,
+        },
+    }
+
+    logger.info(f"Retrieving Semgrep dependencies for deployment '{deployment_id}'.")
+    while has_more:
+        try:
+            response = requests.post(deps_url, json=request_data, headers=headers, timeout=_TIMEOUT)
+            response.raise_for_status()
+            data = response.json()
+        except (ReadTimeout, HTTPError):
+            logger.warning(f"Failed to retrieve Semgrep dependencies for page {page}. Retrying...")
+            retries += 1
+            if retries >= _MAX_RETRIES:
+                raise
+            continue
+        deps = data.get("dependencies", [])
+        has_more = data.get("hasMore", False)
+        logger.info(f"Processed page {page} of Semgrep dependencies.")
+        all_deps.extend(deps)
+        retries = 0
+        page += 1
+        request_data["cursor"] = data.get("cursor")
+
+    logger.info(f"Retrieved {len(all_deps)} Semgrep dependencies in {page} pages.")
+    return all_deps
+
+
+def transform_dependencies(raw_deps: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
+    """
+    Transforms the raw dependencies response from Semgrep API into a list of dicts
+    that can be used to create the Dependency nodes.
+    """
+
+    """
+    sample raw_dep as of November 2024:
+    {
+        "repositoryId": "123456",
+        "definedAt": {
+            "path": "go.mod",
+            "startLine": "6",
+            "endLine": "6",
+            "url": "https://github.com/org/repo-name/blob/00000000000000000000000000000000/go.mod#L6",
+            "committedAt": "1970-01-01T00:00:00Z",
+            "startCol": "0",
+            "endCol": "0"
+        },
+        "transitivity": "DIRECT",
+        "package": {
+            "name": "github.com/foo/bar",
+            "versionSpecifier": "1.2.3"
+        },
+        "ecosystem": "gomod",
+        "licenses": [],
+        "pathToTransitivity": []
+    },
+    """
+    deps = []
+    for raw_dep in raw_deps:
+
+        # We could call a different endpoint to get all repo IDs and store a mapping of repo ID to URL,
+        # but it's much simpler to just extract the URL from the definedAt field.
+        repo_url = raw_dep["definedAt"]["url"].split("/blob/", 1)[0]
+
+        name = raw_dep["package"]["name"]
+        version = raw_dep["package"]["versionSpecifier"]
+        id = f"{name}|{version}"
+
+        # As of November 2024, Semgrep does not import dependencies with version specifiers such as >, <, etc.
+        # For now, hardcode the specifier to ==<version> to align with GitHub-sourced Python dependencies.
+        # If Semgrep eventually supports version specifiers, update this line accordingly.
+        specifier = f"=={version}"
+
+        deps.append({
+            # existing dependency properties:
+            "id": id,
+            "name": name,
+            "specifier": specifier,
+            "version": version,
+            "repo_url": repo_url,
+
+            # Semgrep-specific properties:
+            "ecosystem": raw_dep["ecosystem"],
+            "transitivity": raw_dep["transitivity"].lower(),
+            "url": raw_dep["definedAt"]["url"],
+        })
+
+    return deps
+
+
+@timeit
+def load_dependencies(
+    neo4j_session: neo4j.Session,
+    dependency_schema: Callable,
+    dependencies: List[Dict],
+    deployment_id: str,
+    update_tag: int,
+) -> None:
+    logger.info(f"Loading {len(dependencies)} {dependency_schema().label} objects into the graph.")
+    load(
+        neo4j_session,
+        dependency_schema(),
+        dependencies,
+        lastupdated=update_tag,
+        DEPLOYMENT_ID=deployment_id,
+    )
+
+
+@timeit
+def cleanup(
+    neo4j_session: neo4j.Session,
+    common_job_parameters: Dict[str, Any],
+) -> None:
+    logger.info("Running Semgrep Go Library cleanup job.")
+    go_libraries_cleanup_job = GraphJob.from_node_schema(
+        SemgrepGoLibrarySchema(), common_job_parameters,
+    )
+    go_libraries_cleanup_job.run(neo4j_session)
+
+
+@timeit
+def sync_dependencies(
+    neo4j_session: neo4j.Session,
+    semgrep_app_token: str,
+    update_tag: int,
+    common_job_parameters: Dict[str, Any],
+) -> None:
+
+    deployment_id = common_job_parameters.get("DEPLOYMENT_ID")
+    if not deployment_id:
+        logger.warning(
+            "Missing Semgrep deployment ID, ensure that sync_deployment() has been called."
+            "Skipping Semgrep dependencies sync job.",
+        )
+        return
+
+    logger.info("Running Semgrep dependencies sync job.")
+
+    # fetch and load dependencies for the Go ecosystem
+    raw_go_deps = get_dependencies(semgrep_app_token, deployment_id, ecosystems=["gomod"])
+    go_deps = transform_dependencies(raw_go_deps)
+    load_dependencies(neo4j_session, SemgrepGoLibrarySchema, go_deps, deployment_id, update_tag)
+
+    cleanup(neo4j_session, common_job_parameters)
+
+    merge_module_sync_metadata(
+        neo4j_session=neo4j_session,
+        group_type='Semgrep',
+        group_id=deployment_id,
+        synced_type='SemgrepDependency',
+        update_tag=update_tag,
+        stat_handler=stat_handler,
+    )

cartography/intel/semgrep/deployment.py

@@ -0,0 +1,67 @@
+import logging
+from typing import Any
+from typing import Dict
+
+import neo4j
+import requests
+
+from cartography.client.core.tx import load
+from cartography.models.semgrep.deployment import SemgrepDeploymentSchema
+from cartography.stats import get_stats_client
+from cartography.util import timeit
+
+logger = logging.getLogger(__name__)
+stat_handler = get_stats_client(__name__)
+_TIMEOUT = (60, 60)
+
+
+@timeit
+def get_deployment(semgrep_app_token: str) -> Dict[str, Any]:
+    """
+    Gets the deployment associated with the passed Semgrep App token.
+    param: semgrep_app_token: The Semgrep App token to use for authentication.
+    """
+    deployment = {}
+    deployment_url = "https://semgrep.dev/api/v1/deployments"
+    headers = {
+        "Content-Type": "application/json",
+        "Authorization": f"Bearer {semgrep_app_token}",
+    }
+    response = requests.get(deployment_url, headers=headers, timeout=_TIMEOUT)
+    response.raise_for_status()
+
+    data = response.json()
+    deployment["id"] = data["deployments"][0]["id"]
+    deployment["name"] = data["deployments"][0]["name"]
+    deployment["slug"] = data["deployments"][0]["slug"]
+
+    return deployment
+
+
+@timeit
+def load_semgrep_deployment(
+    neo4j_session: neo4j.Session, deployment: Dict[str, Any], update_tag: int,
+) -> None:
+    logger.info(f"Loading SemgrepDeployment {deployment} into the graph.")
+    load(
+        neo4j_session,
+        SemgrepDeploymentSchema(),
+        [deployment],
+        lastupdated=update_tag,
+    )
+
+
+@timeit
+def sync_deployment(
+    neo4j_session: neo4j.Session,
+    semgrep_app_token: str,
+    update_tag: int,
+    common_job_parameters: Dict[str, Any],
+) -> None:
+
+    semgrep_deployment = get_deployment(semgrep_app_token)
+    deployment_id = semgrep_deployment["id"]
+    deployment_slug = semgrep_deployment["slug"]
+    load_semgrep_deployment(neo4j_session, semgrep_deployment, update_tag)
+    common_job_parameters["DEPLOYMENT_ID"] = deployment_id
+    common_job_parameters["DEPLOYMENT_SLUG"] = deployment_slug

cartography/intel/semgrep/findings.py

@@ -3,14 +3,14 @@ from typing import Any
 from typing import Dict
 from typing import List
 from typing import Tuple
-from urllib.error import HTTPError
 
 import neo4j
 import requests
+from requests.exceptions import HTTPError
+from requests.exceptions import ReadTimeout
 
 from cartography.client.core.tx import load
 from cartography.graph.job import GraphJob
-from cartography.models.semgrep.deployment import SemgrepDeploymentSchema
 from cartography.models.semgrep.findings import SemgrepSCAFindingSchema
 from cartography.models.semgrep.locations import SemgrepSCALocationSchema
 from cartography.stats import get_stats_client
@@ -20,88 +20,97 @@ from cartography.util import timeit
 
 logger = logging.getLogger(__name__)
 stat_handler = get_stats_client(__name__)
+_PAGE_SIZE = 500
 _TIMEOUT = (60, 60)
 _MAX_RETRIES = 3
 
 
 @timeit
-def get_deployment(semgrep_app_token: str) -> Dict[str, Any]:
-    """
-    Gets the deployment associated with the passed Semgrep App token.
-    param: semgrep_app_token: The Semgrep App token to use for authentication.
-    """
-    deployment = {}
-    deployment_url = "https://semgrep.dev/api/v1/deployments"
-    headers = {
-        "Content-Type": "application/json",
-        "Authorization": f"Bearer {semgrep_app_token}",
-    }
-    response = requests.get(deployment_url, headers=headers, timeout=_TIMEOUT)
-    response.raise_for_status()
-
-    data = response.json()
-    deployment["id"] = data["deployments"][0]["id"]
-    deployment["name"] = data["deployments"][0]["name"]
-    deployment["slug"] = data["deployments"][0]["slug"]
-
-    return deployment
-
-
-@timeit
-def get_sca_vulns(semgrep_app_token: str, deployment_id: str) -> List[Dict[str, Any]]:
+def get_sca_vulns(semgrep_app_token: str, deployment_slug: str) -> List[Dict[str, Any]]:
     """
     Gets the SCA vulns associated with the passed Semgrep App token and deployment id.
     param: semgrep_app_token: The Semgrep App token to use for authentication.
-    param: deployment_id: The Semgrep deployment id to use for retrieving SCA vulns.
+    param: deployment_slug: The Semgrep deployment slug to use for retrieving SCA vulns.
     """
     all_vulns = []
-    sca_url = f"https://semgrep.dev/api/v1/deployments/{deployment_id}/ssc-vulns"
+    sca_url = f"https://semgrep.dev/api/v1/deployments/{deployment_slug}/findings"
     has_more = True
-    cursor: Dict[str, str] = {}
-    page = 1
+    page = 0
     retries = 0
     headers = {
         "Content-Type": "application/json",
         "Authorization": f"Bearer {semgrep_app_token}",
     }
 
-    request_data = {
-        "deploymentId": deployment_id,
-        "pageSize": 100,
-        "exposure": ["UNREACHABLE", "REACHABLE", "UNKNOWN_EXPOSURE"],
-        "refs": ["_default"],
+    request_data: dict[str, Any] = {
+        "page": page,
+        "page_size": _PAGE_SIZE,
+        "issue_type": "sca",
+        "exposures": "reachable,always_reachable,conditionally_reachable,unreachable,unknown",
+        "ref": "_default",
+        "dedup": "true",
     }
-
+    logger.info(f"Retrieving Semgrep SCA vulns for deployment '{deployment_slug}'.")
     while has_more:
 
-        if cursor:
-            request_data.update({
-                "cursor": {
-                    "vulnOffset": cursor["vulnOffset"],
-                    "issueOffset": cursor["issueOffset"],
-                },
-            })
         try:
-            response = requests.post(sca_url, json=request_data, headers=headers, timeout=_TIMEOUT)
+            response = requests.get(sca_url, params=request_data, headers=headers, timeout=_TIMEOUT)
             response.raise_for_status()
             data = response.json()
-        except HTTPError as e:
+        except (ReadTimeout, HTTPError):
             logger.warning(f"Failed to retrieve Semgrep SCA vulns for page {page}. Retrying...")
             retries += 1
             if retries >= _MAX_RETRIES:
-                raise e
+                raise
             continue
-        vulns = data["vulns"]
-        cursor = data.get("cursor")
-        has_more = data.get("hasMore", False)
+        vulns = data["findings"]
+        has_more = len(vulns) > 0
         if page % 10 == 0:
-            logger.info(f"Processed {page} pages of Semgrep SCA vulnerabilities so far.")
+            logger.info(f"Processed page {page} of Semgrep SCA vulnerabilities.")
         all_vulns.extend(vulns)
         retries = 0
+        page += 1
+        request_data["page"] = page
 
+    logger.info(f"Retrieved {len(all_vulns)} Semgrep SCA vulns in {page} pages.")
     return all_vulns
 
 
+def _get_vuln_class(vuln: Dict) -> str:
+    vulnerability_classes = vuln["rule"].get("vulnerability_classes", [])
+    if vulnerability_classes:
+        return vulnerability_classes[0]
+    return "Other"
+
+
+def _determine_exposure(vuln: Dict[str, Any]) -> str | None:
+    # See Semgrep reachability types:
+    # https://semgrep.dev/docs/semgrep-supply-chain/overview#types-of-semgrep-supply-chain-findings
+    reachability_types = {
+        "NO REACHABILITY ANALYSIS": 2,
+        "UNREACHABLE": 2,
+        "REACHABLE": 0,
+        "ALWAYS REACHABLE": 0,
+        "CONDITIONALLY REACHABLE": 1,
+    }
+    reachable_flag = vuln["reachability"]
+    if reachable_flag and reachable_flag.upper() in reachability_types:
+        reach_score = reachability_types[reachable_flag.upper()]
+        if reach_score < reachability_types["UNREACHABLE"]:
+            return "REACHABLE"
+        else:
+            return "UNREACHABLE"
+    return None
+
+
+def _build_vuln_url(vuln: str) -> str | None:
+    if 'CVE' in vuln:
+        return f"https://nvd.nist.gov/vuln/detail/{vuln}"
+    if 'GHSA' in vuln:
+        return f"https://github.com/advisories/{vuln}"
+    return None
+
+
 def transform_sca_vulns(raw_vulns: List[Dict[str, Any]]) -> Tuple[List[Dict[str, Any]], List[Dict[str, str]]]:
     """
     Transforms the raw SCA vulns response from Semgrep API into a list of dicts
@@ -112,60 +121,60 @@ def transform_sca_vulns(raw_vulns: List[Dict[str, Any]]) -> Tuple[List[Dict[str,
     for vuln in raw_vulns:
         sca_vuln: Dict[str, Any] = {}
         # Mandatory fields
-        sca_vuln["id"] = vuln["groupKey"]
-        sca_vuln["repositoryName"] = vuln["repositoryName"]
-        sca_vuln["ruleId"] = vuln["advisory"]["ruleId"]
-        sca_vuln["title"] = vuln["advisory"]["title"]
-        sca_vuln["description"] = vuln["advisory"]["description"]
-        sca_vuln["ecosystem"] = vuln["advisory"]["ecosystem"]
-        sca_vuln["severity"] = vuln["advisory"]["severity"]
-        sca_vuln["reachability"] = vuln["advisory"]["reachability"]
-        sca_vuln["reachableIf"] = vuln["advisory"]["reachableIf"]
-        sca_vuln["exposureType"] = vuln["exposureType"]
-        dependency = f"{vuln['matchedDependency']['name']}|{vuln['matchedDependency']['versionSpecifier']}"
+        repository_name = vuln["repository"]["name"]
+        rule_id = vuln["rule"]["name"]
+        vulnerability_class = _get_vuln_class(vuln)
+        package = vuln['found_dependency']['package']
+        sca_vuln["id"] = vuln["id"]
+        sca_vuln["repositoryName"] = repository_name
+        sca_vuln["branch"] = vuln["ref"]
+        sca_vuln["ruleId"] = rule_id
+        sca_vuln["title"] = package + ":" + vulnerability_class
+        sca_vuln["description"] = vuln["rule"]["message"]
+        sca_vuln["ecosystem"] = vuln["found_dependency"]["ecosystem"]
+        sca_vuln["severity"] = vuln["severity"].upper()
+        sca_vuln["reachability"] = vuln["reachability"].upper()  # Check done to determine rechabilitity
+        sca_vuln["reachableIf"] = vuln["reachable_condition"].upper() if vuln["reachable_condition"] else None
+        sca_vuln["exposureType"] = _determine_exposure(vuln)  # Determintes if reachable or unreachable
+        dependency = f"{package}|{vuln['found_dependency']['version']}"
         sca_vuln["matchedDependency"] = dependency
-        sca_vuln["dependencyFileLocation_path"] = vuln["dependencyFileLocation"]["path"]
-        sca_vuln["dependencyFileLocation_url"] = vuln["dependencyFileLocation"]["url"]
-        # Optional fields
-        sca_vuln["transitivity"] = vuln.get("transitivity", None)
-        cves = vuln.get("advisory", {}).get("references", {}).get("cveIds")
-        if len(cves) > 0:
-            # Take the first CVE
-            sca_vuln["cveId"] = vuln["advisory"]["references"]["cveIds"][0]
-        if vuln.get('closestSafeDependency'):
-            dep_fix = f"{vuln['closestSafeDependency']['name']}|{vuln['closestSafeDependency']['versionSpecifier']}"
+        dep_url = vuln["found_dependency"]["lockfile_line_url"]
+        if dep_url:  # Lock file can be null, need to set
+            dep_file = dep_url.split("/")[-1].split("#")[0]
+            sca_vuln["dependencyFileLocation_path"] = dep_file
+            sca_vuln["dependencyFileLocation_url"] = dep_url
+        else:
+            if sca_vuln.get("location"):
+                sca_vuln["dependencyFileLocation_path"] = sca_vuln["location"]["file_path"]
+        sca_vuln["transitivity"] = vuln["found_dependency"]["transitivity"].upper()
+        if vuln.get("vulnerability_identifier"):
+            vuln_id = vuln["vulnerability_identifier"].upper()
+            sca_vuln["cveId"] = vuln_id
+            sca_vuln["ref_urls"] = [_build_vuln_url(vuln_id)]
+        if vuln.get('fix_recommendations') and len(vuln['fix_recommendations']) > 0:
+            fix = vuln['fix_recommendations'][0]
+            dep_fix = f"{fix['package']}|{fix['version']}"
             sca_vuln["closestSafeDependency"] = dep_fix
-        if vuln["advisory"].get("references", {}).get("urls", []):
-            sca_vuln["ref_urls"] = vuln["advisory"].get("references", {}).get("urls", [])
-        sca_vuln["openedAt"] = vuln.get("openedAt", None)
-        sca_vuln["announcedAt"] = vuln.get("announcedAt", None)
-        sca_vuln["fixStatus"] = vuln["triage"]["status"]
-        for usage in vuln.get("usages", []):
+        sca_vuln["openedAt"] = vuln["created_at"]
+        sca_vuln["fixStatus"] = vuln["status"]
+        sca_vuln["triageStatus"] = vuln["triage_state"]
+        sca_vuln["confidence"] = vuln["confidence"]
+        usage = vuln.get("usage")
+        if usage:
             usage_dict = {}
+            url = usage["location"]["url"]
             usage_dict["SCA_ID"] = sca_vuln["id"]
-            usage_dict["findingId"] = usage["findingId"]
+            usage_dict["findingId"] = hash(url.split("github.com/")[-1])
             usage_dict["path"] = usage["location"]["path"]
-            usage_dict["startLine"] = usage["location"]["startLine"]
-            usage_dict["startCol"] = usage["location"]["startCol"]
-            usage_dict["endLine"] = usage["location"]["endLine"]
-            usage_dict["endCol"] = usage["location"]["endCol"]
-            usage_dict["url"] = usage["location"]["url"]
+            usage_dict["startLine"] = usage["location"]["start_line"]
+            usage_dict["startCol"] = usage["location"]["start_col"]
+            usage_dict["endLine"] = usage["location"]["end_line"]
+            usage_dict["endCol"] = usage["location"]["end_col"]
+            usage_dict["url"] = url
             usages.append(usage_dict)
         vulns.append(sca_vuln)
-    return vulns, usages
 
-
-@timeit
-def load_semgrep_deployment(
-    neo4j_session: neo4j.Session, deployment: Dict[str, Any], update_tag: int,
-) -> None:
-    logger.info(f"Loading Semgrep deployment info {deployment} into the graph...")
-    load(
-        neo4j_session,
-        SemgrepDeploymentSchema(),
-        [deployment],
-        lastupdated=update_tag,
-    )
+    return vulns, usages
 
 
 @timeit
@@ -175,7 +184,7 @@ def load_semgrep_sca_vulns(
     deployment_id: str,
     update_tag: int,
 ) -> None:
-    logger.info(f"Loading {len(vulns)} Semgrep SCA vulns info into the graph.")
+    logger.info(f"Loading {len(vulns)} SemgrepSCAFinding objects into the graph.")
     load(
         neo4j_session,
         SemgrepSCAFindingSchema(),
@@ -192,7 +201,7 @@ def load_semgrep_sca_usages(
     deployment_id: str,
     update_tag: int,
 ) -> None:
-    logger.info(f"Loading {len(usages)} Semgrep SCA usages info into the graph.")
+    logger.info(f"Loading {len(usages)} SemgrepSCALocation objects into the graph.")
     load(
         neo4j_session,
         SemgrepSCALocationSchema(),
@@ -219,25 +228,32 @@ def cleanup(
 
 
 @timeit
-def sync(
-    neo4j_sesion: neo4j.Session,
+def sync_findings(
+    neo4j_session: neo4j.Session,
     semgrep_app_token: str,
     update_tag: int,
     common_job_parameters: Dict[str, Any],
 ) -> None:
+
+    deployment_id = common_job_parameters.get("DEPLOYMENT_ID")
+    deployment_slug = common_job_parameters.get("DEPLOYMENT_SLUG")
+    if not deployment_id or not deployment_slug:
+        logger.warning(
+            "Missing Semgrep deployment ID or slug, ensure that sync_deployment() has been called."
+            "Skipping SCA findings sync job.",
+        )
+        return
+
     logger.info("Running Semgrep SCA findings sync job.")
-    semgrep_deployment = get_deployment(semgrep_app_token)
-    deployment_id = semgrep_deployment["id"]
-    load_semgrep_deployment(neo4j_sesion, semgrep_deployment, update_tag)
-    common_job_parameters["DEPLOYMENT_ID"] = deployment_id
-    raw_vulns = get_sca_vulns(semgrep_app_token, deployment_id)
+    raw_vulns = get_sca_vulns(semgrep_app_token, deployment_slug)
     vulns, usages = transform_sca_vulns(raw_vulns)
-    load_semgrep_sca_vulns(neo4j_sesion, vulns, deployment_id, update_tag)
-    load_semgrep_sca_usages(neo4j_sesion, usages, deployment_id, update_tag)
-    run_scoped_analysis_job('semgrep_sca_risk_analysis.json', neo4j_sesion, common_job_parameters)
-    cleanup(neo4j_sesion, common_job_parameters)
+    load_semgrep_sca_vulns(neo4j_session, vulns, deployment_id, update_tag)
+    load_semgrep_sca_usages(neo4j_session, usages, deployment_id, update_tag)
+    run_scoped_analysis_job('semgrep_sca_risk_analysis.json', neo4j_session, common_job_parameters)
+
+    cleanup(neo4j_session, common_job_parameters)
     merge_module_sync_metadata(
-        neo4j_session=neo4j_sesion,
+        neo4j_session=neo4j_session,
         group_type='Semgrep',
         group_id=deployment_id,
         synced_type='SCA',

cartography/intel/snipeit/__init__.py

@@ -0,0 +1,30 @@
+import logging
+
+import neo4j
+
+from cartography.config import Config
+from cartography.intel.snipeit import asset
+from cartography.intel.snipeit import user
+from cartography.stats import get_stats_client
+from cartography.util import timeit
+
+logger = logging.getLogger(__name__)
+stat_handler = get_stats_client(__name__)
+
+
+@timeit
+def start_snipeit_ingestion(neo4j_session: neo4j.Session, config: Config) -> None:
+    if config.snipeit_base_uri is None or config.snipeit_token is None or config.snipeit_tenant_id is None:
+        logger.warning(
+            "Required parameter(s) missing. Skipping sync.",
+        )
+        return
+
+    common_job_parameters = {
+        "UPDATE_TAG": config.update_tag,
+        "TENANT_ID": config.snipeit_tenant_id,
+    }
+
+    # Ingest SnipeIT users and assets
+    user.sync(neo4j_session, common_job_parameters, config.snipeit_base_uri, config.snipeit_token)
+    asset.sync(neo4j_session, common_job_parameters, config.snipeit_base_uri, config.snipeit_token)