fix(agent,service): SEC-002 — validate certificate_id shape + contain key path

Sprint 1 unified-master-audit closure. Pre-fix the agent built its
on-disk key path via:

  keyPath := filepath.Join(a.config.KeyDir, job.CertificateID+".key")

migrations/000001_initial_schema.up.sql declares managed_certificates.id
as TEXT PRIMARY KEY with no shape constraint, so a compromised control
plane (or a poisoned database row) could deliver a job whose
certificate_id is '../../etc/passwd', '/absolute/path', a NUL-byte
payload, or a Windows-separator-laden string — driving arbitrary
file write or read on the agent host.

Fix (two ends; both load-bearing):

Server side:
  - New internal/validation/certificate_id.go: ValidateCertificateID
    pins the canonical TEXT-PK shape (^[A-Za-z0-9._-]{1,128}$, plus
    explicit '.'/'..' rejection).
  - CertificateService.Create now invokes ValidateCertificateID after
    the existing required-fields check; malformed IDs are refused
    before persistence or downstream job creation.

Agent side:
  - cmd/agent/keymem.go: validateAgentCertID mirrors the server-side
    shape regex. safeAgentKeyPath additionally asserts the joined
    path is contained within KeyDir via filepath.Rel — even if a
    future refactor bypasses the shape check, a path that escapes
    KeyDir fails closed.
  - poll.go + deploy.go: both filepath.Join call sites routed
    through safeAgentKeyPath; rejection surfaces via reportJobStatus
    so the control plane sees the failure.

Regression coverage:
  - internal/validation/certificate_id_test.go: production shapes
    accepted; explicit rejection table for empty, overlong, posix
    traversal, absolute, Windows traversal, Windows separator, NUL
    byte, newline/tab injection, drive prefix, space, unicode dots.
  - cmd/agent/keymem_test.go: validateAgentCertID acceptance +
    rejection tables; safeAgentKeyPath happy path + the 8 audit
    vectors plus empty-keyDir refusal.

Closes SEC-002.

cmd/agent/deploy.go

@@ -11,7 +11,6 @@ import (
 	"io"
 	"net/http"
 	"os"
-	"path/filepath"
 	"strings"
 
 	"github.com/certctl-io/certctl/internal/connector/target"
@@ -105,8 +104,24 @@ func (a *Agent) executeDeploymentJob(ctx context.Context, job JobItem) {
 	// Split PEM into cert and chain (separated by double newline between PEM blocks)
 	certOnly, chainPEM := splitPEMChain(certPEM)
 
-	// Check for locally-stored private key (agent keygen mode)
-	keyPath := filepath.Join(a.config.KeyDir, job.CertificateID+".key")
+	// Check for locally-stored private key (agent keygen mode).
+	//
+	// SEC-002 closure (Sprint 1, 2026-05-16): safeAgentKeyPath validates
+	// the certificate_id shape AND asserts the joined path is contained
+	// within a.config.KeyDir. A crafted certificate_id (path traversal,
+	// absolute path, NUL byte, Windows separators) fails closed before
+	// any disk I/O. See cmd/agent/keymem.go for the helper.
+	keyPath, kerr := safeAgentKeyPath(a.config.KeyDir, job.CertificateID)
+	if kerr != nil {
+		a.logger.Error("agent key path validation failed for deployment",
+			"job_id", job.ID,
+			"certificate_id", job.CertificateID,
+			"error", kerr)
+		if reportErr := a.reportJobStatus(ctx, job.ID, "Failed", fmt.Sprintf("key path validation failed: %v", kerr)); reportErr != nil {
+			a.logger.Error("failed to report job status to server", "job_id", job.ID, "error", reportErr)
+		}
+		return
+	}
 	var keyPEM string
 	keyData, err := os.ReadFile(keyPath)
 	if err != nil {

cmd/agent/keymem.go

@@ -9,6 +9,8 @@ import (
 	"fmt"
 	"os"
 	"path/filepath"
+	"regexp"
+	"strings"
 )
 
 // Bundle-9 / Audit L-002 + L-003 (agent edition).
@@ -41,6 +43,87 @@ func marshalAgentKeyAndZeroize(priv *ecdsa.PrivateKey, onDER func([]byte) error)
 	return onDER(der)
 }
 
+// SEC-002 closure (Sprint 1, 2026-05-16). The agent derives an on-disk
+// key path from job.CertificateID via filepath.Join. Pre-fix, a
+// crafted certificate_id ("../../etc/passwd", "/absolute/path",
+// "abc\x00d", "..\\Windows\\path") would drive arbitrary file
+// write/read on the agent host. The shape regex below mirrors the
+// server-side internal/validation.ValidateCertificateID gate — both
+// ends MUST hold for the load-bearing defense (the server can't be
+// trusted in isolation; a compromised control plane could deliver a
+// crafted job).
+//
+// agentCertIDPattern accepts ASCII letters, digits, ".", "_", "-",
+// bounded to 128 chars. Existing prefixed IDs (mc-..., cert-..., etc.)
+// satisfy this trivially. Deliberately rejects path separators (POSIX
+// and Windows), NUL byte, whitespace, control characters, and the
+// bare relative-path tokens "." and "..".
+var agentCertIDPattern = regexp.MustCompile(`^[A-Za-z0-9._-]{1,128}$`)
+
+// validateAgentCertID returns an error if id is not a well-formed
+// certificate identifier. Mirrors internal/validation.ValidateCertificateID
+// — the duplication is deliberate per the package-level comment
+// ("cmd/agent is a separate binary; copy-paste cheaper than lifting
+// a shared internal/keystore for a single shape check").
+func validateAgentCertID(id string) error {
+	if id == "" {
+		return fmt.Errorf("certificate_id is required")
+	}
+	if len(id) > 128 {
+		return fmt.Errorf("certificate_id length %d exceeds 128", len(id))
+	}
+	if !agentCertIDPattern.MatchString(id) {
+		return fmt.Errorf("certificate_id %q contains disallowed characters", id)
+	}
+	if id == "." || id == ".." {
+		return fmt.Errorf("certificate_id %q is a relative-path token", id)
+	}
+	return nil
+}
+
+// safeAgentKeyPath returns the on-disk key path for the given
+// certificateID, after validating the ID shape AND asserting the
+// joined path is contained within keyDir. Containment is the
+// authoritative guard — even if validateAgentCertID is bypassed (e.g.
+// a future refactor removes it), the post-Clean rel-path check below
+// rejects any path that escapes keyDir.
+//
+// The two-leg defense:
+//
+//	leg 1: shape check (validateAgentCertID)  → cheap up-front fail
+//	leg 2: containment check (filepath.Rel)   → load-bearing guard
+//
+// Returns the joined path on success, or a non-nil error describing
+// the rejected vector.
+func safeAgentKeyPath(keyDir, certificateID string) (string, error) {
+	if err := validateAgentCertID(certificateID); err != nil {
+		return "", err
+	}
+	if keyDir == "" {
+		return "", fmt.Errorf("safeAgentKeyPath: empty keyDir")
+	}
+	cleanDir, err := filepath.Abs(filepath.Clean(keyDir))
+	if err != nil {
+		return "", fmt.Errorf("safeAgentKeyPath: resolve keyDir: %w", err)
+	}
+	joined := filepath.Join(cleanDir, certificateID+".key")
+	cleanJoined := filepath.Clean(joined)
+	rel, err := filepath.Rel(cleanDir, cleanJoined)
+	if err != nil {
+		return "", fmt.Errorf("safeAgentKeyPath: rel(%q,%q): %w", cleanDir, cleanJoined, err)
+	}
+	// Reject any path that escapes the directory: a leading ".." in the
+	// relative form means the joined path resolved outside keyDir.
+	if rel == ".." || strings.HasPrefix(rel, ".."+string(filepath.Separator)) {
+		return "", fmt.Errorf("safeAgentKeyPath: %q escapes keyDir %q (rel=%q)", certificateID, cleanDir, rel)
+	}
+	// Belt-and-suspenders: the rel form must also not contain a NUL.
+	if strings.ContainsRune(rel, 0) {
+		return "", fmt.Errorf("safeAgentKeyPath: NUL byte in computed path")
+	}
+	return cleanJoined, nil
+}
+
 // ensureAgentKeyDirSecure creates dir (and ancestors) with mode 0700 or
 // asserts an existing dir is owner-only. If a pre-existing dir is more
 // permissive than 0700 we tighten it to 0700 (logging-free; this is a

cmd/agent/keymem_test.go

@@ -716,3 +716,113 @@ func TestKeymem_AgentMainFlowSmoke(t *testing.T) {
 		}
 	}
 }
+
+// =============================================================================
+// SEC-002 closure (Sprint 1, 2026-05-16) — safeAgentKeyPath path-traversal
+// regression coverage.
+//
+// Pre-fix the agent built the on-disk key path via:
+//
+//	keyPath := filepath.Join(a.config.KeyDir, job.CertificateID+".key")
+//
+// migrations/000001_initial_schema.up.sql declares
+// managed_certificates.id as TEXT PRIMARY KEY with no shape constraint, so
+// a crafted certificate_id from a compromised control plane (or a poisoned
+// DB row) could land outside KeyDir. The fix:
+//
+//   - validateAgentCertID rejects shape violations up-front
+//   - safeAgentKeyPath additionally asserts the joined path is contained
+//     within KeyDir via filepath.Rel; even a future refactor that drops
+//     the shape regex would still fail closed on escape.
+//
+// These tests pin both legs against the four vectors called out in the
+// audit (../../etc/passwd, /absolute/path, NUL byte, Windows separators).
+// =============================================================================
+
+func TestValidateAgentCertID_AcceptsCanonicalShapes(t *testing.T) {
+	for _, id := range []string{
+		"mc-cdn-edge",
+		"mc-cdn-edge-2026.q1",
+		"cert-1",
+		"abc123",
+		"MC-UPPER",
+	} {
+		t.Run(id, func(t *testing.T) {
+			if err := validateAgentCertID(id); err != nil {
+				t.Errorf("validateAgentCertID(%q): unexpected error %v", id, err)
+			}
+		})
+	}
+}
+
+func TestValidateAgentCertID_RejectsTraversalVectors(t *testing.T) {
+	cases := []struct {
+		name string
+		id   string
+	}{
+		{"empty", ""},
+		{"parent_token", ".."},
+		{"current_token", "."},
+		{"posix_traversal", "../../etc/passwd"},
+		{"absolute_posix", "/absolute/path"},
+		{"windows_traversal", `..\..\evil`},
+		{"windows_separator", `bad\path`},
+		{"nul_byte", "abc\x00def"},
+		{"newline", "abc\ndef"},
+		{"space", "id with spaces"},
+		{"overlong", strings.Repeat("a", 129)},
+	}
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			if err := validateAgentCertID(tc.id); err == nil {
+				t.Errorf("id=%q: expected rejection, got nil", tc.id)
+			}
+		})
+	}
+}
+
+func TestSafeAgentKeyPath_HappyPath_ProducesContainedPath(t *testing.T) {
+	keyDir := t.TempDir()
+	got, err := safeAgentKeyPath(keyDir, "mc-good")
+	if err != nil {
+		t.Fatalf("safeAgentKeyPath: %v", err)
+	}
+	want := filepath.Join(keyDir, "mc-good.key")
+	// filepath.Clean normalisation may strip a trailing separator, etc.;
+	// compare canonical forms.
+	if filepath.Clean(got) != filepath.Clean(want) {
+		t.Errorf("safeAgentKeyPath = %q; want %q", got, want)
+	}
+}
+
+func TestSafeAgentKeyPath_RejectsTraversalVectors(t *testing.T) {
+	keyDir := t.TempDir()
+	cases := []struct {
+		name string
+		id   string
+	}{
+		{"posix_traversal", "../../etc/passwd"},
+		{"absolute_posix", "/etc/passwd"},
+		{"parent_token", ".."},
+		{"current_token", "."},
+		{"windows_traversal", `..\..\evil`},
+		{"windows_separator", `bad\path`},
+		{"nul_byte", "abc\x00def"},
+		{"empty", ""},
+	}
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			_, err := safeAgentKeyPath(keyDir, tc.id)
+			if err == nil {
+				t.Errorf("id=%q: expected rejection, got nil", tc.id)
+			}
+		})
+	}
+}
+
+func TestSafeAgentKeyPath_RejectsEmptyKeyDir(t *testing.T) {
+	_, err := safeAgentKeyPath("", "mc-good")
+	if err == nil {
+		t.Errorf("empty keyDir: expected rejection, got nil")
+	}
+}

cmd/agent/poll.go

@@ -151,7 +151,20 @@ func (a *Agent) executeCSRJob(ctx context.Context, job JobItem) {
 	// before any write touches disk. Also defer-clear the PEM buffer for
 	// the same reason — the encoded key isn't sensitive in transit (it's
 	// going to disk) but lingers on the heap if we don't.
-	keyPath := filepath.Join(a.config.KeyDir, job.CertificateID+".key")
+	//
+	// SEC-002 closure (Sprint 1, 2026-05-16): safeAgentKeyPath validates
+	// the certificate_id shape AND asserts the joined path is contained
+	// within a.config.KeyDir. A crafted certificate_id like
+	// "../../etc/passwd" or "/abs/path" now fails closed before any
+	// disk I/O. See cmd/agent/keymem.go for the helper.
+	keyPath, kerr := safeAgentKeyPath(a.config.KeyDir, job.CertificateID)
+	if kerr != nil {
+		a.logger.Error("agent key path validation failed", "job_id", job.ID, "certificate_id", job.CertificateID, "error", kerr)
+		if reportErr := a.reportJobStatus(ctx, job.ID, "Failed", fmt.Sprintf("key path validation failed: %v", kerr)); reportErr != nil {
+			a.logger.Error("failed to report job status to server", "job_id", job.ID, "status", "Failed", "error", reportErr)
+		}
+		return
+	}
 	if err := ensureAgentKeyDirSecure(filepath.Dir(keyPath)); err != nil {
 		a.logger.Error("agent key dir hardening failed", "job_id", job.ID, "error", err)
 		if reportErr := a.reportJobStatus(ctx, job.ID, "Failed", fmt.Sprintf("key dir hardening failed: %v", err)); reportErr != nil {