Add inline DSSE provenance documentation and Mongo schema

- Introduced a new document outlining the inline DSSE provenance for SBOM, VEX, scan, and derived events.
- Defined the Mongo schema for event patches, including key fields for provenance and trust verification.
- Documented the write path for ingesting provenance metadata and backfilling historical events.
- Created CI/CD snippets for uploading DSSE attestations and generating provenance metadata.
- Established Mongo indexes for efficient provenance queries and provided query recipes for various use cases.
- Outlined policy gates for managing VEX decisions based on provenance verification.
- Included UI nudges for displaying provenance information and implementation tasks for future enhancements.

---

Implement reachability lattice and scoring model

- Developed a comprehensive document detailing the reachability lattice and scoring model.
- Defined core types for reachability states, evidence, and mitigations with corresponding C# models.
- Established a scoring policy with base score contributions from various evidence classes.
- Mapped reachability states to VEX gates and provided a clear overview of evidence sources.
- Documented the event graph schema for persisting reachability data in MongoDB.
- Outlined the integration of runtime probes for evidence collection and defined a roadmap for future tasks.

---

Introduce uncertainty states and entropy scoring

- Created a draft document for tracking uncertainty states and their impact on risk scoring.
- Defined core uncertainty states with associated entropy values and evidence requirements.
- Established a schema for storing uncertainty states alongside findings.
- Documented the risk score calculation incorporating uncertainty and its effect on final risk assessments.
- Provided policy guidelines for handling uncertainty in decision-making processes.
- Outlined UI guidelines for displaying uncertainty information and suggested remediation actions.

---

Add Ruby package inventory management

- Implemented Ruby package inventory management with corresponding data models and storage mechanisms.
- Created C# records for Ruby package inventory, artifacts, provenance, and runtime details.
- Developed a repository for managing Ruby package inventory documents in MongoDB.
- Implemented a service for storing and retrieving Ruby package inventories.
- Added unit tests for the Ruby package inventory store to ensure functionality and data integrity.
This commit is contained in:
master
2025-11-13 00:20:33 +02:00
parent 86be324fc0
commit 7040984215
41 changed files with 1955 additions and 76 deletions

View File

@@ -0,0 +1,121 @@
using System.Collections.Generic;
using Microsoft.Extensions.Options;
using MongoDB.Driver;
using StellaOps.Scanner.Core.Contracts;
using StellaOps.Scanner.Storage;
using StellaOps.Scanner.Storage.Mongo;
using StellaOps.Scanner.Storage.Repositories;
using StellaOps.Scanner.Storage.Services;
using StellaOps.Scanner.Storage.Catalog;
using Xunit;
namespace StellaOps.Scanner.Storage.Tests;
public sealed class RubyPackageInventoryStoreTests : IClassFixture<ScannerMongoFixture>
{
private readonly ScannerMongoFixture _fixture;
public RubyPackageInventoryStoreTests(ScannerMongoFixture fixture)
{
_fixture = fixture;
}
[Fact]
public async Task StoreAsync_ThrowsWhenInventoryNull()
{
var store = CreateStore();
await Assert.ThrowsAsync<ArgumentNullException>(async () =>
{
RubyPackageInventory? inventory = null;
await store.StoreAsync(inventory!, CancellationToken.None);
});
}
[Fact]
public async Task GetAsync_ReturnsNullWhenMissing()
{
await ClearCollectionAsync();
var store = CreateStore();
var inventory = await store.GetAsync("scan-missing", CancellationToken.None);
Assert.Null(inventory);
}
[Fact]
public async Task StoreAsync_RoundTripsInventory()
{
await ClearCollectionAsync();
var store = CreateStore();
var scanId = $"scan-{Guid.NewGuid():n}";
var generatedAt = new DateTimeOffset(2025, 11, 12, 16, 10, 0, TimeSpan.Zero);
var packages = new[]
{
new RubyPackageArtifact(
Id: "purl::pkg:gem/rack@3.1.2",
Name: "rack",
Version: "3.1.2",
Source: "rubygems",
Platform: "ruby",
Groups: new[] {"default"},
DeclaredOnly: true,
RuntimeUsed: true,
Provenance: new RubyPackageProvenance("rubygems", "Gemfile.lock", "Gemfile.lock"),
Runtime: new RubyPackageRuntime(
new[] { "config.ru" },
new[] { "config.ru" },
new[] { "require-static" }),
Metadata: new Dictionary<string, string?>(StringComparer.OrdinalIgnoreCase)
{
["source"] = "rubygems",
["lockfile"] = "Gemfile.lock",
["groups"] = "default"
})
};
var inventory = new RubyPackageInventory(scanId, "sha256:image", generatedAt, packages);
await store.StoreAsync(inventory, CancellationToken.None);
var stored = await store.GetAsync(scanId, CancellationToken.None);
Assert.NotNull(stored);
Assert.Equal(scanId, stored!.ScanId);
Assert.Equal("sha256:image", stored.ImageDigest);
Assert.Equal(generatedAt, stored.GeneratedAtUtc);
Assert.Single(stored.Packages);
Assert.Equal("rack", stored.Packages[0].Name);
Assert.Equal("rubygems", stored.Packages[0].Source);
}
private async Task ClearCollectionAsync()
{
var provider = CreateProvider();
await provider.RubyPackages.DeleteManyAsync(Builders<RubyPackageInventoryDocument>.Filter.Empty);
}
private RubyPackageInventoryStore CreateStore()
{
var provider = CreateProvider();
var repository = new RubyPackageInventoryRepository(provider);
return new RubyPackageInventoryStore(repository);
}
private MongoCollectionProvider CreateProvider()
{
var options = Options.Create(new ScannerStorageOptions
{
Mongo = new MongoOptions
{
ConnectionString = _fixture.Runner.ConnectionString,
DatabaseName = _fixture.Database.DatabaseNamespace.DatabaseName,
UseMajorityReadConcern = false,
UseMajorityWriteConcern = false
}
});
return new MongoCollectionProvider(_fixture.Database, options);
}
}

View File

@@ -13,6 +13,7 @@ using Microsoft.AspNetCore.Http;
using Microsoft.AspNetCore.Mvc.Testing;
using Microsoft.AspNetCore.TestHost;
using Microsoft.Extensions.DependencyInjection;
using StellaOps.Scanner.Core.Contracts;
using StellaOps.Scanner.EntryTrace;
using StellaOps.Scanner.EntryTrace.Serialization;
using StellaOps.Scanner.Storage.Catalog;
@@ -365,6 +366,66 @@ public sealed class ScansEndpointsTests
Assert.Equal(ndjson, payload.Ndjson);
}
[Fact]
public async Task RubyPackagesEndpointReturnsNotFoundWhenMissing()
{
using var factory = new ScannerApplicationFactory();
using var client = factory.CreateClient();
var response = await client.GetAsync("/api/v1/scans/scan-ruby-missing/ruby-packages");
Assert.Equal(HttpStatusCode.NotFound, response.StatusCode);
}
[Fact]
public async Task RubyPackagesEndpointReturnsInventory()
{
const string scanId = "scan-ruby-existing";
const string digest = "sha256:feedfacefeedfacefeedfacefeedfacefeedfacefeedfacefeedfacefeedface";
var generatedAt = DateTime.UtcNow.AddMinutes(-10);
using var factory = new ScannerApplicationFactory();
using (var scope = factory.Services.CreateScope())
{
var repository = scope.ServiceProvider.GetRequiredService<RubyPackageInventoryRepository>();
var document = new RubyPackageInventoryDocument
{
ScanId = scanId,
ImageDigest = digest,
GeneratedAtUtc = generatedAt,
Packages = new List<RubyPackageDocument>
{
new()
{
Id = "pkg:gem/rack@3.1.0",
Name = "rack",
Version = "3.1.0",
Source = "rubygems",
Platform = "ruby",
Groups = new List<string> { "default" },
RuntimeUsed = true,
Provenance = new RubyPackageProvenance("rubygems", "Gemfile.lock", "Gemfile.lock")
}
}
};
await repository.UpsertAsync(document, CancellationToken.None).ConfigureAwait(false);
}
using var client = factory.CreateClient();
var response = await client.GetAsync($"/api/v1/scans/{scanId}/ruby-packages");
Assert.Equal(HttpStatusCode.OK, response.StatusCode);
var payload = await response.Content.ReadFromJsonAsync<RubyPackagesResponse>();
Assert.NotNull(payload);
Assert.Equal(scanId, payload!.ScanId);
Assert.Equal(digest, payload.ImageDigest);
Assert.Single(payload.Packages);
Assert.Equal("rack", payload.Packages[0].Name);
Assert.Equal("rubygems", payload.Packages[0].Source);
}
private sealed class RecordingCoordinator : IScanCoordinator
{
private readonly IHttpContextAccessor accessor;

View File

@@ -10,5 +10,6 @@
<ItemGroup>
<ProjectReference Include="../../StellaOps.Scanner.Worker/StellaOps.Scanner.Worker.csproj" />
<ProjectReference Include="../../__Libraries/StellaOps.Scanner.Queue/StellaOps.Scanner.Queue.csproj" />
<ProjectReference Include="../../__Libraries/StellaOps.Scanner.Analyzers.Lang.Ruby/StellaOps.Scanner.Analyzers.Lang.Ruby.csproj" />
</ItemGroup>
</Project>
</Project>

View File

@@ -1,6 +1,7 @@
using System;
using System.Collections.Generic;
using System.Collections.Immutable;
using System.Collections.ObjectModel;
using System.IO;
using System.Linq;
using System.Text;
@@ -11,6 +12,8 @@ using System.Threading.Tasks;
using System.Security.Cryptography;
using Microsoft.Extensions.Logging.Abstractions;
using Microsoft.Extensions.Options;
using StellaOps.Scanner.Analyzers.Lang;
using StellaOps.Scanner.Analyzers.Lang.Ruby;
using StellaOps.Scanner.Core.Contracts;
using StellaOps.Scanner.EntryTrace;
using StellaOps.Scanner.Surface.Env;
@@ -44,7 +47,8 @@ public sealed class SurfaceManifestStageExecutorTests
environment,
metrics,
NullLogger<SurfaceManifestStageExecutor>.Instance,
hash);
hash,
new NullRubyPackageInventoryStore());
var context = CreateContext();
@@ -80,7 +84,8 @@ public sealed class SurfaceManifestStageExecutorTests
environment,
metrics,
NullLogger<SurfaceManifestStageExecutor>.Instance,
hash);
hash,
new NullRubyPackageInventoryStore());
var context = CreateContext();
PopulateAnalysis(context);
@@ -158,6 +163,69 @@ public sealed class SurfaceManifestStageExecutorTests
context.Analysis.Set(ScanAnalysisKeys.LayerComponentFragments, ImmutableArray.Create(fragment));
}
[Fact]
public async Task ExecuteAsync_PersistsRubyPackageInventoryWhenResultsExist()
{
var metrics = new ScannerWorkerMetrics();
var publisher = new TestSurfaceManifestPublisher("tenant-a");
var cache = new RecordingSurfaceCache();
var environment = new TestSurfaceEnvironment("tenant-a");
var hash = CreateCryptoHash();
var packageStore = new RecordingRubyPackageStore();
var executor = new SurfaceManifestStageExecutor(
publisher,
cache,
environment,
metrics,
NullLogger<SurfaceManifestStageExecutor>.Instance,
hash,
packageStore);
var context = CreateContext();
PopulateAnalysis(context);
await PopulateRubyAnalyzerResultsAsync(context);
await executor.ExecuteAsync(context, CancellationToken.None);
Assert.NotNull(packageStore.LastInventory);
Assert.Equal(context.ScanId, packageStore.LastInventory!.ScanId);
Assert.NotEmpty(packageStore.LastInventory!.Packages);
}
private static async Task PopulateRubyAnalyzerResultsAsync(ScanJobContext context)
{
var fixturePath = Path.Combine(
ResolveRepositoryRoot(),
"src",
"Scanner",
"__Tests",
"StellaOps.Scanner.Analyzers.Lang.Ruby.Tests",
"Fixtures",
"lang",
"ruby",
"simple-app");
var analyzer = new RubyLanguageAnalyzer();
var engine = new LanguageAnalyzerEngine(new ILanguageAnalyzer[] { analyzer });
var analyzerContext = new LanguageAnalyzerContext(
fixturePath,
TimeProvider.System,
usageHints: null,
services: null,
analysisStore: context.Analysis);
var result = await engine.AnalyzeAsync(analyzerContext, CancellationToken.None);
var dictionary = new Dictionary<string, LanguageAnalyzerResult>(StringComparer.OrdinalIgnoreCase)
{
["ruby"] = result
};
context.Analysis.Set(
ScanAnalysisKeys.LanguageAnalyzerResults,
new ReadOnlyDictionary<string, LanguageAnalyzerResult>(dictionary));
}
[Fact]
public async Task ExecuteAsync_IncludesDenoObservationPayloadWhenPresent()
{
@@ -172,7 +240,8 @@ public sealed class SurfaceManifestStageExecutorTests
environment,
metrics,
NullLogger<SurfaceManifestStageExecutor>.Instance,
hash);
hash,
new NullRubyPackageInventoryStore());
var context = CreateContext();
var observationBytes = Encoding.UTF8.GetBytes("{\"entrypoints\":[\"mod.ts\"]}");
@@ -390,6 +459,36 @@ public sealed class SurfaceManifestStageExecutorTests
}
}
private sealed class RecordingRubyPackageStore : IRubyPackageInventoryStore
{
public RubyPackageInventory? LastInventory { get; private set; }
public Task StoreAsync(RubyPackageInventory inventory, CancellationToken cancellationToken)
{
LastInventory = inventory;
return Task.CompletedTask;
}
public Task<RubyPackageInventory?> GetAsync(string scanId, CancellationToken cancellationToken)
=> Task.FromResult(LastInventory);
}
private static string ResolveRepositoryRoot()
{
var directory = AppContext.BaseDirectory;
while (!string.IsNullOrWhiteSpace(directory))
{
if (Directory.Exists(Path.Combine(directory, ".git")))
{
return directory;
}
directory = Path.GetDirectoryName(directory) ?? string.Empty;
}
throw new InvalidOperationException("Repository root not found.");
}
private sealed class FakeJobLease : IScanJobLease
{
private readonly Dictionary<string, string> _metadata = new()