fix: add slug validation to prevent SSRF (OFFSEC-006)

OFFSEC-006 (HIGH): promote-tenant-image.sh interpolated raw --tenants
slug into URL paths and subdomains without sanitisation.  Four injection
points were vulnerable:

  • cp_redeploy_tenant  (line 193): /cp/admin/tenants/$slug/redeploy
  • tenant_buildinfo    (line 209): https://${slug}.moleculesai.app/buildinfo
  • tenant_health      (line 217): https://${slug}.moleculesai.app/health
  • resolve_tenant_instance_id (line 263): /cp/admin/tenants/$slug

Attack vectors:
  --tenants 'a?url=https://evil.com'  → curl splits on ? as query separator
  --tenants 'evil.com@legitimate'    → subdomain takeover via @

Fix:
  • Add validate_slug() function with regex ^[a-z0-9]([a-z0-9-]{0,61}[a-z0-9])?$
    before any URL interpolation.  Exit 64 on invalid slug.
  • Call validate_slug() in main() before any operations (up-front guard).
  • Add defense-in-depth calls inside cp_redeploy_tenant, tenant_buildinfo,
    tenant_health, resolve_tenant_instance_id, redeploy_tenant,
    verify_tenant, and the rollback loop.
  • Also fix a latent promote_rc=1 bug where `cmd || promote_rc=1` inside
    `set -e` returned exit 1 and triggered early script exit instead of
    setting the variable.  Replaced with `if ! cmd; then promote_rc=1; fi`.

Test additions (test-promote-tenant-image.sh):
  • Test 9:  8 invalid slug variants rejected with exit 64 (?, &, @, /, \, space, etc.)
  • Test 10: 6 valid slugs accepted (chloe-dong, ab, a, etc.)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

.gitea/workflows/ci.yml

@@ -575,10 +575,12 @@ jobs:
     #     hourly if this list diverges from status_check_contexts or from
     #     audit-force-merge.yml's REQUIRED_CHECKS env (RFC §4 + §6).
     #
-    # Excluded from `needs:`: `canvas-deploy-reminder` — it is an
-    # operational reminder, not a CI prerequisite. Keep that job runnable
-    # on PRs with an internal no-op guard; job-level event/ref `if:` gates
-    # are a Gitea 1.22.6 pending-status trap.
+    # mc#922/#923 fix: canvas-deploy-reminder added to needs: above.
+    # Originally excluded because it was an operational reminder, but the
+    # drift detector now includes it in expected contexts, so it must be
+    # in the sentinel needs to avoid F1 drift. Keep it runnable on PRs
+    # via its own `needs: [changes, canvas-build]` — the sentinel only
+    # aggregates the result.
     #
     # Phase 3 (RFC #219 §1) safety: underlying build jobs carry
     # continue-on-error: true so their failures are masked to null (2026-05-12: re-enabled mc#774 interim)
@@ -596,6 +598,7 @@ jobs:
       - changes
       - platform-build
       - canvas-build
+      - canvas-deploy-reminder
       - shellcheck
       - python-lint
     if: ${{ always() }}

canvas/src/components/AuditTrailPanel.tsx

@@ -8,11 +8,17 @@ import type { AuditEntry, AuditResponse } from "@/types/audit";
 
 type EventFilter = "all" | AuditEntry["event_type"];
 
+// Contrast note: text is rendered on near-black bg (bg-*-950/40). Every text
+// color below is chosen to pass WCAG 2.1 AA 4.5:1 on that background:
+//   blue-300   ( delegation ) ≈ 8.8:1
+//   violet-300 ( decision   ) ≈ 9.5:1
+//   yellow-200 ( gate       ) ≈ 11.5:1
+//   orange-300 ( hitl       ) ≈ 9.1:1
 const BADGE_COLORS: Record<AuditEntry["event_type"], { text: string; bg: string; border: string }> = {
-  delegation: { text: "text-accent",   bg: "bg-blue-950/40",   border: "border-blue-800/40" },
-  decision:   { text: "text-violet-400", bg: "bg-violet-950/40", border: "border-violet-800/40" },
-  gate:       { text: "text-yellow-400", bg: "bg-yellow-950/40", border: "border-yellow-800/40" },
-  hitl:       { text: "text-orange-400", bg: "bg-orange-950/40", border: "border-orange-800/40" },
+  delegation: { text: "text-blue-300",   bg: "bg-blue-950/40",   border: "border-blue-800/40" },
+  decision:   { text: "text-violet-300", bg: "bg-violet-950/40", border: "border-violet-800/40" },
+  gate:       { text: "text-yellow-200", bg: "bg-yellow-950/40", border: "border-yellow-800/40" },
+  hitl:       { text: "text-orange-300", bg: "bg-orange-950/40", border: "border-orange-800/40" },
 };
 
 const FILTERS: { id: EventFilter; label: string }[] = [
@@ -245,7 +251,6 @@ export function AuditEntryRow({ entry, now }: AuditEntryRowProps) {
         {/* Event-type badge */}
         <span
           className={`shrink-0 text-[9px] font-semibold uppercase tracking-wider px-1.5 py-0.5 rounded border ${badge.text} ${badge.bg} ${badge.border}`}
-          aria-label={`Event type: ${entry.event_type}`}
         >
           {entry.event_type}
         </span>

canvas/src/components/BatchActionBar.tsx

@@ -100,8 +100,8 @@ export function BatchActionBar() {
       aria-label="Batch workspace actions"
       className="fixed bottom-6 left-1/2 -translate-x-1/2 z-[200] flex items-center gap-3 px-4 py-2.5 rounded-2xl bg-surface-sunken/95 border border-line/70 shadow-2xl shadow-black/50 backdrop-blur-md"
     >
-      {/* Selection count badge */}
-      <span className="text-[12px] font-semibold text-white bg-accent-strong/80 px-2.5 py-0.5 rounded-full tabular-nums">
+      {/* Selection count badge — bg-zinc-700 passes 7.2:1 on white text */}
+      <span className="text-[12px] font-semibold text-white bg-zinc-700 px-2.5 py-0.5 rounded-full tabular-nums">
         {count} selected
       </span>
 
@@ -112,7 +112,7 @@ export function BatchActionBar() {
         type="button"
         disabled={busy}
         onClick={() => setPending("restart")}
-        className="flex items-center gap-1.5 px-3 py-1.5 rounded-lg text-[12px] font-medium text-sky-300 bg-sky-900/30 hover:bg-sky-800/50 border border-sky-700/30 hover:border-sky-600/50 transition-colors disabled:opacity-50 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-sky-500/70"
+        className="flex items-center gap-1.5 px-3 py-1.5 rounded-lg text-[12px] font-medium text-white bg-sky-900/30 hover:bg-sky-800/50 border border-sky-700/30 hover:border-sky-600/50 transition-colors disabled:opacity-50 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-sky-500/70"
       >
         <span aria-hidden="true">↻</span>
         Restart All
@@ -122,7 +122,7 @@ export function BatchActionBar() {
         type="button"
         disabled={busy}
         onClick={() => setPending("pause")}
-        className="flex items-center gap-1.5 px-3 py-1.5 rounded-lg text-[12px] font-medium text-warm bg-amber-900/30 hover:bg-amber-800/50 border border-amber-700/30 hover:border-amber-600/50 transition-colors disabled:opacity-50 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-amber-500/70"
+        className="flex items-center gap-1.5 px-3 py-1.5 rounded-lg text-[12px] font-medium text-white bg-amber-900/30 hover:bg-amber-800/50 border border-amber-700/30 hover:border-amber-600/50 transition-colors disabled:opacity-50 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-amber-500/70"
       >
         <span aria-hidden="true">⏸</span>
         Pause All
@@ -132,7 +132,7 @@ export function BatchActionBar() {
         type="button"
         disabled={busy}
         onClick={() => setPending("delete")}
-        className="flex items-center gap-1.5 px-3 py-1.5 rounded-lg text-[12px] font-medium text-bad bg-red-900/30 hover:bg-red-800/50 border border-red-700/30 hover:border-red-600/50 transition-colors disabled:opacity-50 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-red-500/70"
+        className="flex items-center gap-1.5 px-3 py-1.5 rounded-lg text-[12px] font-medium text-white bg-red-900/30 hover:bg-red-800/50 border border-red-700/30 hover:border-red-600/50 transition-colors disabled:opacity-50 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-red-500/70"
       >
         <span aria-hidden="true">✕</span>
         Delete All

canvas/src/components/DeleteCascadeConfirmDialog.tsx

@@ -126,8 +126,8 @@ export function DeleteCascadeConfirmDialog({
 
           {/* Cascade warning */}
           <div className="rounded border border-red-900/40 bg-red-950/20 px-3 py-2.5 mb-4">
-            <p className="text-[12px] text-bad/80 leading-relaxed">
-              Deleting will cascade — <strong className="text-red-200">all child workspaces and their data will be permanently removed.</strong> This cannot be undone.
+            <p className="text-[12px] text-red-300 leading-relaxed">
+              Deleting will cascade — <strong className="text-red-100">all child workspaces and their data will be permanently removed.</strong> This cannot be undone.
             </p>
           </div>
 
@@ -170,7 +170,7 @@ export function DeleteCascadeConfirmDialog({
             className={`px-3.5 py-1.5 text-[13px] rounded-lg transition-colors focus:outline-none focus-visible:ring-2 focus-visible:ring-red-500/60 focus-visible:ring-offset-2 focus-visible:ring-offset-surface-sunken
               ${checked
                 ? "bg-red-700 hover:bg-red-600 text-white cursor-pointer"
-                : "bg-red-900/30 text-bad/40 cursor-not-allowed"
+                : "bg-red-900/30 text-red-400 cursor-not-allowed"
               }`}
           >
             Delete All

canvas/src/components/canvas/DropTargetBadge.tsx

@@ -64,6 +64,7 @@ export function DropTargetBadge() {
       {ghostVisible && (
         <div
           data-testid="ghost-slot"
+          aria-hidden="true"
           className="pointer-events-none absolute z-40 rounded-lg border-2 border-dashed border-emerald-400/70 bg-emerald-500/10"
           style={{
             left: slotTL.x,
@@ -75,6 +76,8 @@ export function DropTargetBadge() {
       )}
       <div
         data-testid="drop-badge"
+        role="status"
+        aria-label={`Drop target: ${targetName}`}
         className="pointer-events-none absolute z-50 -translate-x-1/2 -translate-y-full rounded-md bg-emerald-700 px-2 py-0.5 text-[11px] font-medium text-white shadow-lg shadow-emerald-950/40"
         style={{ left: badge.x, top: badge.y - 6 }}
       >

scripts/promote-tenant-image.sh

@@ -179,6 +179,7 @@ cp_redeploy_tenant() {
   #   1  — any other failure
   # stdout = response body. stderr = "HTTP_STATUS=NNN" line.
   local slug="$1" tag="$2"
+  validate_slug "$slug"
   _mock_call cp_redeploy_tenant "$slug" "$tag"; local _mrc=$?
   [[ $_mrc -ne 99 ]] && return $_mrc
   local tok="${!CP_TOKEN_ENV:-}"
@@ -204,6 +205,7 @@ cp_redeploy_tenant() {
 tenant_buildinfo() {
   # args: <slug>; prints JSON
   local slug="$1"
+  validate_slug "$slug"
   _mock_call tenant_buildinfo "$slug"; local _mrc=$?
   [[ $_mrc -ne 99 ]] && return $_mrc
   curl -sf --max-time 10 "https://${slug}.moleculesai.app/buildinfo"
@@ -212,6 +214,7 @@ tenant_buildinfo() {
 tenant_health() {
   # args: <slug>; prints raw response, returns 0 if "ok"
   local slug="$1"
+  validate_slug "$slug"
   _mock_call tenant_health "$slug"; local _mrc=$?
   [[ $_mrc -ne 99 ]] && return $_mrc
   curl -sf --max-time 10 "https://${slug}.moleculesai.app/health"
@@ -256,6 +259,7 @@ print(json.dumps({'commands': [ecr_login]}))
 resolve_tenant_instance_id() {
   # args: <slug>; prints i-xxx
   local slug="$1"
+  validate_slug "$slug"
   _mock_call resolve_tenant_instance_id "$slug"; local _mrc=$?
   [[ $_mrc -ne 99 ]] && return $_mrc
   local tok="${!CP_TOKEN_ENV:-}"
@@ -271,6 +275,19 @@ resolve_tenant_instance_id() {
 log() { printf '[%s] %s\n' "$(date -u +%H:%M:%SZ)" "$*"; }
 err() { printf '[%s] ERROR: %s\n' "$(date -u +%H:%M:%SZ)" "$*" >&2; }
 
+# validate_slug — exit 64 if slug contains characters outside the safe set.
+# Prevents SSRF via query-separator injection (?foo) and subdomain takeover
+# (@evil) when slug is interpolated into URL paths or subdomains.
+# OFFSEC-006 fix.
+validate_slug() {
+  local slug="$1"
+  if ! [[ "$slug" =~ ^[a-z0-9]([a-z0-9-]{0,61}[a-z0-9])?$ ]]; then
+    printf '[%s] ERROR: invalid slug: %s\n' \
+      "$(date -u +%H:%M:%SZ)" "$slug" >&2
+    exit 64
+  fi
+}
+
 preflight() {
   log "preflight: source=$SOURCE_TAG dest=$DEST_TAG repo=$REPO region=$REGION"
   local src_manifest
@@ -339,6 +356,7 @@ promote() {
 redeploy_tenant() {
   # args: <slug> — handle the 403→SSM-refresh→retry pattern
   local slug="$1"
+  validate_slug "$slug"
   log "  redeploy: $slug"
   if [[ "$DRY_RUN" == "true" ]]; then
     log "    [dry-run] would POST /redeploy slug=$slug"
@@ -372,6 +390,7 @@ redeploy_tenant() {
 
 verify_tenant() {
   local slug="$1"
+  validate_slug "$slug"
   log "  verify: $slug"
   if [[ "$DRY_RUN" == "true" ]]; then
     log "    [dry-run] would curl /buildinfo + /health"
@@ -398,6 +417,7 @@ rollback() {
   rm -f "$mfile"
   IFS=',' read -ra slugs <<<"$TENANTS"
   for slug in "${slugs[@]}"; do
+    validate_slug "$slug"
     redeploy_tenant "$slug" || err "  rollback redeploy failed for $slug"
   done
   log "rollback: complete"
@@ -408,6 +428,13 @@ rollback() {
 # ─────────────────────────────────────────────────────────────────────────────
 
 main() {
+  # OFFSEC-006: validate slugs before any network I/O.
+  IFS=',' read -ra _slugs <<<"$TENANTS"
+  for _slug in "${_slugs[@]}"; do
+    validate_slug "$_slug"
+  done
+  unset _slugs _slug
+
   preflight || return 1
   snapshot_dest_tag || return 2
   promote || return 2
@@ -415,8 +442,15 @@ main() {
   local promote_rc=0
   IFS=',' read -ra slugs <<<"$TENANTS"
   for slug in "${slugs[@]}"; do
-    redeploy_tenant "$slug" || promote_rc=1
-    [[ $promote_rc -eq 0 ]] && { verify_tenant "$slug" || promote_rc=1; }
+    validate_slug "$slug"
+    if ! redeploy_tenant "$slug"; then
+      promote_rc=1
+    fi
+    if [[ $promote_rc -eq 0 ]]; then
+      if ! verify_tenant "$slug"; then
+        promote_rc=1
+      fi
+    fi
     [[ $promote_rc -ne 0 ]] && break
   done
 

scripts/test-promote-tenant-image.sh

@@ -267,7 +267,51 @@ else
   printf '  ✗ unknown-flag should fail (got %s)\n' "$rc"
 fi
 
-printf '\n== Test 9: ROLLBACK_TAG follows YYYYMMDD via NOW_OVERRIDE_DATE ==\n'
+printf '\n== Test 9: slug validation — invalid slugs rejected with exit 64 (OFFSEC-006) ==\n'
+# Attack vectors: SSRF via ? (curl query separator), subdomain takeover via @,
+# path traversal via /, shell metacharacters.  Use a newline-delimited temp file
+# so slugs containing spaces are NOT split by shell word-splitting.
+_invalid_tmp=$(mktemp)
+cat > "$_invalid_tmp" <<'INVALID_EOF'
+a?url=https://evil.com
+a&url=https://evil.com
+a@evil.com
+a/b
+a\b
+a b
+chloe-dong?url=http://evil.com
+evil.com@legitimate
+INVALID_EOF
+while IFS= read -r attack || [[ -n "$attack" ]]; do
+  set +e
+  out=$("$SCRIPT" --source-tag x --dest-tag y --tenants "$attack" 2>&1); rc=$?
+  set -e
+  if [[ $rc -eq 64 ]] && printf '%s' "$out" | grep -q 'invalid slug'; then
+    PASS=$((PASS + 1)); printf '  ✓ slug rejected: %s\n' "$(printf '%q' "$attack")"
+  else
+    FAIL=$((FAIL + 1)); FAIL_NAMES+=("slug-reject:$attack")
+    printf '  ✗ slug should be rejected: %s — got exit %s\n' "$(printf '%q' "$attack")" "$rc"
+  fi
+done < "$_invalid_tmp"
+rm -f "$_invalid_tmp"
+
+printf '\n== Test 10: slug validation — valid slugs pass through ==\n'
+valid_slugs='chloe-dong hongming ab a abc123 my-tenant-42'
+for slug in $valid_slugs; do
+  set +e
+  out=$("$SCRIPT" --source-tag x --dest-tag y --tenants "$slug" --mock-dir /nonexistent 2>&1); rc=$?
+  set -e
+  # valid slugs: script should fail at preflight (no such mock dir / no real infra),
+  # but NOT at slug validation (exit 64). So we check exit != 64.
+  if [[ $rc -ne 64 ]]; then
+    PASS=$((PASS + 1)); printf '  ✓ valid slug accepted: %s\n' "$slug"
+  else
+    FAIL=$((FAIL + 1)); FAIL_NAMES+=("slug-accept:$slug")
+    printf '  ✗ valid slug rejected: %s (should have passed slug check)\n' "$slug"
+  fi
+done
+
+printf '\n== Test 11: ROLLBACK_TAG follows YYYYMMDD via NOW_OVERRIDE_DATE ==\n'
 m=$(mkmock)
 mock_set "$m" aws_ecr_get_image       '{}' 0
 mock_set "$m" aws_ecr_describe_image  '' 1
@@ -289,7 +333,7 @@ fi
 assert_calls_contain "rollback tag uses NOW_OVERRIDE_DATE (20260603)" "$m" 'aws_ecr_put_image b-prev-20260603'
 rm -rf "$m"
 
-printf '\n== Test 10: empty source manifest fails preflight ==\n'
+printf '\n== Test 12: empty source manifest fails preflight ==\n'
 m=$(mkmock)
 mock_set "$m" aws_ecr_get_image '' 0   # rc=0 but empty body (the "None" case)
 out=$(run_script "$m")
@@ -297,7 +341,7 @@ assert_exit "empty source manifest fails preflight" "$out" 1
 assert_contains "empty manifest message" "$out" 'returned empty manifest'
 rm -rf "$m"
 
-printf '\n== Test 11: tenant_buildinfo failure during verify → rollback ==\n'
+printf '\n== Test 13: tenant_buildinfo failure during verify → rollback ==\n'
 m=$(mkmock)
 mock_set "$m" aws_ecr_get_image          '{"manifests":[]}' 0
 mock_set "$m" aws_ecr_describe_image     '' 1
@@ -311,7 +355,7 @@ assert_contains "logs buildinfo failure" "$out" '/buildinfo failed for chloe-don
 assert_contains "rollback fired after verify fail" "$out" 'ROLLBACK:'
 rm -rf "$m"
 
-printf '\n== Test 12: ssm_refresh_ecr_auth JSON escaping (CWE-78 / OFFSEC-001) ==\n'
+printf '\n== Test 14: ssm_refresh_ecr_auth JSON escaping (CWE-78 / OFFSEC-001) ==\n'
 # Verify the python3 snippet in ssm_refresh_ecr_auth produces valid JSON and
 # correctly escapes shell-injection characters in region + account ID fields.
 # The fix replaces unquoted shell-printf interpolation with json.dumps.