Files
certctl/internal/service/audit.go
T
shankar0123 f5ba17114d fix(audit): close silence-leg of HIGH-6; emit WARN on audit-write failure
Audit 2026-05-10 HIGH-6 partial closure (silence leg). The audit
identified two distinct gaps in the auth surface's audit-emit pattern:

  (1) silence — `_ = audit.RecordEventWithCategory(...)` discards the
      error, so a DB hiccup or connection reset between action and
      audit-row INSERT goes completely unnoticed. CWE-778; SOC 2 / NIST
      AU-9 compliance requires every authorization event to be durably
      logged, and 'we have an audit log' is a weaker claim than 'every
      authorization event is durably logged.'

  (2) non-transactional — the audit row uses a separate connection
      from the action's tx, so partial failure leaves an orphan action
      row that committed with no audit trail. Decision 8 of the
      auth-bundles-index requires action + audit row atomic.

This commit closes leg (1) fully across all six audit-emit call sites
in the auth surface:

  - internal/service/auth/actor_role_service.go::recordAudit
  - internal/service/auth/role_service.go::recordAudit
  - internal/auth/bootstrap/service.go::ValidateAndMint
  - internal/auth/breakglass/service.go::recordAudit
  - internal/auth/session/service.go::recordAudit
  - internal/api/handler/auth_session_oidc.go::recordAudit
  - internal/service/profile.go::Update (Phase 9 approval-bypass)

Each `_ = ...` swallow is replaced with:

  if err := audit.RecordEventWithCategory(...); err != nil {
      slog.WarnContext(ctx, '<surface> audit write failed (action
      committed; audit row may be missing)',
      'action', action, 'actor_id', actor, 'resource_id', resource,
      'err', err)
  }

Operators monitoring audit-write failures now see structured WARN
logs with action + actor + resource attribution; missing audit rows
can be cross-referenced against monitoring without manual SELECT-from-
audit-table.

Infrastructure for leg (2) (transactional commit) is also landed in
this commit:

  - service.AuditService.RecordEventWithCategoryWithTx (new method;
    accepts repository.Querier from postgres.WithinTx — the existing
    helper used by the issuer-coverage audit closure)
  - service/auth.AuditService interface declares the new method
  - test stub fakeAudit.RecordEventWithCategoryWithTx satisfies the
    extended interface

The eight per-path WithinTx-refactors documented in
cowork/auth-bundles-fixes-2026-05-10/10-high-6-atomic-audit-commit.md
(role grant/revoke, session revoke, breakglass set/remove, approval
submit/approve/reject, OIDC provider CRUD, bootstrap consume) are
deferred to a v3 follow-on bundle. Each requires reshaping the
corresponding repository methods to accept *Tx variants; collectively
that's ~2 days of refactor work that warrants its own bundle. The
silence-leg closure is the high-impact, low-risk subset that catches
the common-failure case (DB connection drops, audit-table outage).

Refs: cowork/auth-bundles-audit-2026-05-10.md HIGH-6
Spec: cowork/auth-bundles-fixes-2026-05-10/10-high-6-atomic-audit-commit.md
2026-05-10 21:24:29 +00:00

268 lines
8.9 KiB
Go

package service
import (
"context"
"encoding/json"
"fmt"
"time"
"github.com/certctl-io/certctl/internal/domain"
"github.com/certctl-io/certctl/internal/repository"
)
// AuditService provides business logic for recording and retrieving audit events.
type AuditService struct {
auditRepo repository.AuditRepository
}
// NewAuditService creates a new audit service.
func NewAuditService(auditRepo repository.AuditRepository) *AuditService {
return &AuditService{
auditRepo: auditRepo,
}
}
// RecordEvent records an audit event with actor, action, and resource information.
//
// Bundle-6 / Audit H-008 + M-022 / CWE-532: every details map flows through
// RedactDetailsForAudit BEFORE marshaling. The redactor scrubs credential
// keys (api_key, password, token, *_pem, eab_secret, ...) and PII keys
// (email, phone, ssn, name, address, ip_address, ...) and surfaces a
// `redacted_keys` array so operators can audit the redactor itself during
// a compliance review. See internal/service/audit_redact.go.
func (s *AuditService) RecordEvent(ctx context.Context, actor string, actorType domain.ActorType, action string, resourceType string, resourceID string, details map[string]interface{}) error {
return s.RecordEventWithCategory(ctx, actor, actorType, action, "", resourceType, resourceID, details)
}
// RecordEventWithCategory is the Bundle 1 Phase 8 categorized variant
// of RecordEvent. eventCategory is one of
// domain.EventCategoryCertLifecycle, domain.EventCategoryAuth,
// domain.EventCategoryConfig — empty defaults to cert_lifecycle in
// the persistence layer + DB CHECK constraint.
//
// Existing 90+ call sites that don't yet pass a category route
// through the legacy RecordEvent and inherit the cert_lifecycle
// default; new callers (auth handlers, bootstrap, config-mutation
// handlers) call this method directly with their explicit category.
// Both paths share the same redaction + marshaling contract.
func (s *AuditService) RecordEventWithCategory(ctx context.Context, actor string, actorType domain.ActorType, action, eventCategory, resourceType, resourceID string, details map[string]interface{}) error {
redacted := RedactDetailsForAudit(details)
detailsJSON, err := json.Marshal(redacted)
if err != nil {
detailsJSON = []byte("{}")
}
event := &domain.AuditEvent{
ID: generateID("audit"),
Timestamp: time.Now(),
Actor: actor,
ActorType: actorType,
Action: action,
ResourceType: resourceType,
ResourceID: resourceID,
Details: json.RawMessage(detailsJSON),
EventCategory: eventCategory,
}
if err := s.auditRepo.Create(ctx, event); err != nil {
return fmt.Errorf("failed to record audit event: %w", err)
}
return nil
}
// RecordEventWithTx records an audit event using the supplied repository.Querier.
//
// Pass *sql.Tx (typically obtained from postgres.WithinTx) to participate in
// a caller's transaction so the audit row is atomic with the operation that
// triggered it. Closes the #3 acquisition-readiness blocker from the
// 2026-05-01 issuer coverage audit (audit row not transactional with the
// operation it audits).
//
// Same redaction + marshalling contract as RecordEvent; only the database
// handle changes.
func (s *AuditService) RecordEventWithTx(ctx context.Context, q repository.Querier, actor string, actorType domain.ActorType, action string, resourceType string, resourceID string, details map[string]interface{}) error {
redacted := RedactDetailsForAudit(details)
detailsJSON, err := json.Marshal(redacted)
if err != nil {
detailsJSON = []byte("{}")
}
event := &domain.AuditEvent{
ID: generateID("audit"),
Timestamp: time.Now(),
Actor: actor,
ActorType: actorType,
Action: action,
ResourceType: resourceType,
ResourceID: resourceID,
Details: json.RawMessage(detailsJSON),
}
if err := s.auditRepo.CreateWithTx(ctx, q, event); err != nil {
return fmt.Errorf("failed to record audit event: %w", err)
}
return nil
}
// RecordEventWithCategoryWithTx records a categorized audit event using
// the supplied repository.Querier so the row is committed in the same
// transaction as the underlying action. Mirrors RecordEventWithCategory
// but takes the Querier (typically *sql.Tx from postgres.WithinTx).
//
// Audit 2026-05-10 HIGH-6 closure — closes the gap where Bundle-1+2
// auth-mutation paths emitted the audit row via a separate, non-
// transactional connection. A DB hiccup or connection reset between
// the action and the audit-row INSERT used to leave the action
// committed with no audit trail (CWE-778). With this method, the
// audit row participates in the action's transaction: rollback on
// any failure removes both the action row AND any audit row that the
// caller wrote inside the tx.
func (s *AuditService) RecordEventWithCategoryWithTx(ctx context.Context, q repository.Querier, actor string, actorType domain.ActorType, action, eventCategory, resourceType, resourceID string, details map[string]interface{}) error {
redacted := RedactDetailsForAudit(details)
detailsJSON, err := json.Marshal(redacted)
if err != nil {
detailsJSON = []byte("{}")
}
event := &domain.AuditEvent{
ID: generateID("audit"),
Timestamp: time.Now(),
Actor: actor,
ActorType: actorType,
Action: action,
ResourceType: resourceType,
ResourceID: resourceID,
Details: json.RawMessage(detailsJSON),
EventCategory: eventCategory,
}
if err := s.auditRepo.CreateWithTx(ctx, q, event); err != nil {
return fmt.Errorf("failed to record audit event: %w", err)
}
return nil
}
// List returns audit events matching filter criteria.
func (s *AuditService) List(ctx context.Context, filter *repository.AuditFilter) ([]*domain.AuditEvent, error) {
events, err := s.auditRepo.List(ctx, filter)
if err != nil {
return nil, fmt.Errorf("failed to list audit events: %w", err)
}
return events, nil
}
// ListByResource returns all audit events for a specific resource.
func (s *AuditService) ListByResource(ctx context.Context, resourceType string, resourceID string) ([]*domain.AuditEvent, error) {
filter := &repository.AuditFilter{
ResourceType: resourceType,
ResourceID: resourceID,
PerPage: 1000, // reasonable default for single resource
}
events, err := s.auditRepo.List(ctx, filter)
if err != nil {
return nil, fmt.Errorf("failed to list audit events: %w", err)
}
return events, nil
}
// ListByActor returns all audit events for a specific actor.
func (s *AuditService) ListByActor(ctx context.Context, actor string) ([]*domain.AuditEvent, error) {
filter := &repository.AuditFilter{
Actor: actor,
PerPage: 1000,
}
events, err := s.auditRepo.List(ctx, filter)
if err != nil {
return nil, fmt.Errorf("failed to list audit events: %w", err)
}
return events, nil
}
// ListByAction returns all audit events for a specific action type.
func (s *AuditService) ListByAction(ctx context.Context, action string, from, to time.Time) ([]*domain.AuditEvent, error) {
filter := &repository.AuditFilter{
From: from,
To: to,
PerPage: 1000,
}
events, err := s.auditRepo.List(ctx, filter)
if err != nil {
return nil, fmt.Errorf("failed to list audit events: %w", err)
}
// Filter by action on client side (repository may not filter by action directly)
var filtered []*domain.AuditEvent
for _, e := range events {
if e.Action == action {
filtered = append(filtered, e)
}
}
return filtered, nil
}
// ListAuditEvents returns paginated audit events (handler interface method).
func (s *AuditService) ListAuditEvents(ctx context.Context, page, perPage int) ([]domain.AuditEvent, int64, error) {
return s.ListAuditEventsByCategory(ctx, "", page, perPage)
}
// ListAuditEventsByCategory is the Bundle 1 Phase 8 categorized variant.
// Empty eventCategory disables the filter.
func (s *AuditService) ListAuditEventsByCategory(ctx context.Context, eventCategory string, page, perPage int) ([]domain.AuditEvent, int64, error) {
if page < 1 {
page = 1
}
if perPage < 1 {
perPage = 50
}
filter := &repository.AuditFilter{
EventCategory: eventCategory,
Page: page,
PerPage: perPage,
}
events, err := s.auditRepo.List(ctx, filter)
if err != nil {
return nil, 0, fmt.Errorf("failed to list audit events: %w", err)
}
// Convert pointers to values for the handler interface
var result []domain.AuditEvent
for _, e := range events {
if e != nil {
result = append(result, *e)
}
}
// TODO: Get total count from repository
total := int64(len(result))
return result, total, nil
}
// GetAuditEvent returns a single audit event (handler interface method).
func (s *AuditService) GetAuditEvent(ctx context.Context, id string) (*domain.AuditEvent, error) {
filter := &repository.AuditFilter{
ResourceID: id,
PerPage: 1,
}
events, err := s.auditRepo.List(ctx, filter)
if err != nil {
return nil, fmt.Errorf("failed to get audit event: %w", err)
}
if len(events) == 0 {
return nil, fmt.Errorf("audit event not found")
}
return events[0], nil
}