Files
certctl/internal/connector/issuer/acme/ari.go
T
Shankar 345bafe5aa Bundle C: Renewal/reliability cluster — 7 findings closed
Closes M-006 + M-007 + M-008 + M-015 + M-016 + M-019 + M-020 from
comprehensive-audit-2026-04-25. M-028 was already closed by the
Bundle B CI follow-up.

M-006 (CWE-913) — Idempotent migration 000014
  migrations/000014_policy_violation_severity_check.up.sql:
    Prepended ALTER TABLE ... DROP CONSTRAINT IF EXISTS before the
    ADD. Mirrors the down migration's existing IF EXISTS shape and
    the M-7 idempotent-index idiom. Re-runs against partially-applied
    DBs now succeed.

M-007 — Bulk-op partial-failure tests (3 new)
  internal/api/handler/bulk_partial_failure_test.go:
    TestBulkRevoke_PartialFailure_ReportsBoth
    TestBulkRenew_PartialFailure_ReportsBoth
    TestBulkReassign_PartialFailure_ReportsBoth
  Each asserts HTTP 200 + both success/failure counters round-trip
  + per-cert errors[] preserved with non-empty messages so operators
  can correlate each failure to its certificate ID.

M-008 — Admin-gated handler enumeration pin (verified-already-clean)
  Recon: only one admin-gated handler — bulk_revocation.go — with
  full 3-branch test triplet already in place. health.go calls
  IsAdmin informationally to surface the flag to the GUI without
  gating.
  internal/api/handler/m008_admin_gate_test.go:
    Walks every handler .go file, asserts every middleware.IsAdmin
    call site is in AdminGatedHandlers (with required test triplet)
    or InformationalIsAdminCallers (justified). Adding a new admin
    gate without updating both the constant AND adding the test
    triplet fails CI.

M-015 — Single-profile cardinality pin (verified-already-clean)
  Audit claim 'no cardinality validation' was wrong — enforced at
  struct level. domain.ManagedCertificate.{CertificateProfileID,
  RenewalPolicyID,IssuerID,OwnerID} and RenewalPolicy.
  CertificateProfileID are bare strings, not slices.
  internal/domain/m015_cardinality_test.go:
    reflect-based pin on kind=String. Schema change to N:N would
    have to update renewal.go's lookup loop in the same commit.

M-016 (CWE-754) — Reap stale-agent jobs
  internal/repository/postgres/job.go::ListJobsWithOfflineAgents:
    JOIN jobs to agents on agent_id, filter (status=Running AND
    a.last_heartbeat_at < cutoff), exclude server-keygen jobs.
  internal/service/job.go::ReapJobsWithOfflineAgents:
    Flips matched jobs to Failed reason agent_offline so I-001
    retry loop re-queues them on a healthy agent. Records audit
    event per reap.
  internal/scheduler/scheduler.go:
    Scheduler.runJobTimeout cycle now calls both reaper arms.
    agentOfflineJobTTL default 5min (5x agent-health-check default);
    SetAgentOfflineJobTTL knob for operator override.
  internal/service/job_offline_agent_reaper_test.go: 6 unit tests
  cover happy path, server-keygen-skip, non-Running-skip, non-
  positive-TTL fail-loud, repo-error propagation, audit-event
  recording.

M-019 — Configurable ARI HTTP timeout
  Audit claim 'no fallback timeout' was wrong — ari.go:52 already
  had a 15s timeout. Bundle C makes it configurable.
  internal/connector/issuer/acme/acme.go:
    Config.ARIHTTPTimeoutSeconds field with env path
    CERTCTL_ACME_ARI_HTTP_TIMEOUT_SECONDS.
  internal/connector/issuer/acme/ari.go:
    Both HTTP clients (GetRenewalInfo + getARIEndpoint) now use the
    new ariHTTPTimeout() helper. Zero / negative / nil-config all
    fall back to the historic 15s default.
  ari_timeout_test.go: 4 dispatch arm tests.

M-020 (CWE-770) — OCSP DoS hardening
  Pre-bundle the noAuthHandler chain had no rate limit. An attacker
  could DoS the OCSP responder, which for fail-open relying parties
  is a revocation bypass.
  cmd/server/main.go:
    noAuthHandler refactored from fixed middleware.Chain(...) to a
    conditional slice that appends middleware.NewRateLimiter when
    cfg.RateLimit.Enabled. Per-IP keying applies; OCSP/CRL/EST/SCEP
    are unauth.
  docs/security.md (NEW):
    Operator runbook documenting Must-Staple TLS Feature extension
    RFC 7633 as the architectural fix for fail-open relying parties.
    Profile-flip guidance + nginx/Apache/HAProxy/Envoy stapling
    snippets + explicit scope statement on what the rate limiter
    alone does NOT solve.

Audit deliverables:
  cowork/comprehensive-audit-2026-04-25/audit-report.md: score
    31/55 -> 38/55 closed (Medium 13/27 -> 20/27).
  cowork/comprehensive-audit-2026-04-25/findings.yaml: 7 status
    flips open -> closed with closure notes citing the Bundle C
    mechanism.
  certctl/CHANGELOG.md: Bundle C section under [unreleased].

Verification:
  go vet ./internal/service ./internal/scheduler ./internal/connector/issuer/acme
    ./internal/api/handler ./internal/domain ./cmd/server     clean
  go test -count=1 -short on the same packages              all green
  helm template + helm lint                                 clean
  internal/repository/postgres setup-fail                   sandbox disk
    pressure (same on master HEAD before this branch)
2026-04-27 00:08:25 +00:00

178 lines
5.7 KiB
Go

package acme
import (
"context"
"crypto/sha256"
"encoding/base64"
"encoding/json"
"encoding/pem"
"fmt"
"io"
"net/http"
"strings"
"time"
"github.com/shankar0123/certctl/internal/connector/issuer"
)
// GetRenewalInfo retrieves ACME Renewal Information (ARI) per RFC 9773 for a certificate.
// certPEM is the PEM-encoded certificate. Returns nil, nil if the CA does not support ARI.
func (c *Connector) GetRenewalInfo(ctx context.Context, certPEM string) (*issuer.RenewalInfoResult, error) {
if !c.config.ARIEnabled {
return nil, nil
}
if err := c.ensureClient(ctx); err != nil {
return nil, fmt.Errorf("ACME client init: %w", err)
}
// Parse the certificate to compute the ARI certificate ID
certID, err := computeARICertID(certPEM)
if err != nil {
return nil, fmt.Errorf("failed to compute ARI cert ID: %w", err)
}
c.logger.Debug("retrieving ARI for certificate",
"cert_id", certID)
// Fetch the ACME directory to find the renewalInfo endpoint
renewalInfoURL, err := c.getARIEndpoint(ctx, certID)
if err != nil {
return nil, fmt.Errorf("failed to construct ARI endpoint: %w", err)
}
c.logger.Debug("querying ARI endpoint", "url", renewalInfoURL)
// Make GET request to the ARI endpoint
req, err := http.NewRequestWithContext(ctx, http.MethodGet, renewalInfoURL, nil)
if err != nil {
return nil, fmt.Errorf("create ARI request: %w", err)
}
httpClient := &http.Client{Timeout: c.ariHTTPTimeout()}
resp, err := httpClient.Do(req)
if err != nil {
return nil, fmt.Errorf("ARI request failed: %w", err)
}
defer resp.Body.Close()
body, err := io.ReadAll(resp.Body)
if err != nil {
return nil, fmt.Errorf("read ARI response: %w", err)
}
// 404 means the CA doesn't support ARI or the cert doesn't exist
if resp.StatusCode == http.StatusNotFound {
c.logger.Debug("ARI not supported by CA or cert not found")
return nil, nil
}
// Other non-2xx errors
if resp.StatusCode < 200 || resp.StatusCode >= 300 {
return nil, fmt.Errorf("ARI endpoint returned status %d: %s", resp.StatusCode, string(body))
}
// Parse the ARI response
var ariResp struct {
SuggestedWindow struct {
Start time.Time `json:"start"`
End time.Time `json:"end"`
} `json:"suggestedWindow"`
RetryAfter time.Time `json:"retryAfter,omitempty"`
ExplanationURL string `json:"explanationURL,omitempty"`
}
if err := json.Unmarshal(body, &ariResp); err != nil {
return nil, fmt.Errorf("parse ARI response: %w", err)
}
if ariResp.SuggestedWindow.Start.IsZero() || ariResp.SuggestedWindow.End.IsZero() {
return nil, fmt.Errorf("invalid ARI response: missing or empty suggestedWindow")
}
c.logger.Info("retrieved ARI",
"window_start", ariResp.SuggestedWindow.Start,
"window_end", ariResp.SuggestedWindow.End)
return &issuer.RenewalInfoResult{
SuggestedWindowStart: ariResp.SuggestedWindow.Start,
SuggestedWindowEnd: ariResp.SuggestedWindow.End,
RetryAfter: ariResp.RetryAfter,
ExplanationURL: ariResp.ExplanationURL,
}, nil
}
// computeARICertID computes the ARI certificate ID as defined in RFC 9773.
// The cert ID is base64url(SHA256(DER encoding of the certificate)).
func computeARICertID(certPEM string) (string, error) {
block, _ := pem.Decode([]byte(certPEM))
if block == nil {
return "", fmt.Errorf("invalid PEM: no certificate block found")
}
hash := sha256.Sum256(block.Bytes)
certID := base64.RawURLEncoding.EncodeToString(hash[:])
return certID, nil
}
// ariHTTPTimeout returns the per-request timeout for ARI HTTP calls. Bundle C
// / Audit M-019: configurable via Config.ARIHTTPTimeoutSeconds (env var
// CERTCTL_ACME_ARI_HTTP_TIMEOUT_SECONDS), defaults to 15 seconds.
func (c *Connector) ariHTTPTimeout() time.Duration {
if c.config != nil && c.config.ARIHTTPTimeoutSeconds > 0 {
return time.Duration(c.config.ARIHTTPTimeoutSeconds) * time.Second
}
return 15 * time.Second
}
// getARIEndpoint constructs the ARI endpoint URL from the ACME directory.
// It fetches the directory JSON and extracts the "renewalInfo" field if available.
// Falls back to a standard URL pattern if the directory doesn't advertise renewalInfo.
func (c *Connector) getARIEndpoint(ctx context.Context, certID string) (string, error) {
// Try to fetch and parse the directory
httpClient := &http.Client{Timeout: c.ariHTTPTimeout()}
req, err := http.NewRequestWithContext(ctx, http.MethodGet, c.config.DirectoryURL, nil)
if err != nil {
return "", fmt.Errorf("create directory request: %w", err)
}
resp, err := httpClient.Do(req)
if err != nil {
// If we can't fetch the directory, try the standard Let's Encrypt pattern
return constructARIURLFallback(c.config.DirectoryURL, certID), nil
}
defer resp.Body.Close()
body, err := io.ReadAll(resp.Body)
if err != nil {
return constructARIURLFallback(c.config.DirectoryURL, certID), nil
}
var dir struct {
RenewalInfo string `json:"renewalInfo,omitempty"`
}
if err := json.Unmarshal(body, &dir); err != nil {
// Malformed directory; use fallback
return constructARIURLFallback(c.config.DirectoryURL, certID), nil
}
if dir.RenewalInfo != "" {
// Directory advertises renewalInfo endpoint
return dir.RenewalInfo + "/" + certID, nil
}
// No renewalInfo in directory; use standard fallback
return constructARIURLFallback(c.config.DirectoryURL, certID), nil
}
// constructARIURLFallback builds an ARI endpoint URL using a standard pattern.
// It replaces "/directory" with "/renewalInfo" in the URL.
func constructARIURLFallback(directoryURL, certID string) string {
// Replace "/directory" with "/renewalInfo/{certID}"
// For Let's Encrypt: https://acme-v02.api.letsencrypt.org/directory
// becomes: https://acme-v02.api.letsencrypt.org/renewalInfo/{certID}
baseURL := strings.TrimSuffix(directoryURL, "/directory")
return baseURL + "/renewalInfo/" + certID
}