diff --git a/.github/workflows/agent-completion-enforcement.yml b/.github/workflows/agent-completion-enforcement.yml
index 1c4fd1b5d..17500b376 100644
--- a/.github/workflows/agent-completion-enforcement.yml
+++ b/.github/workflows/agent-completion-enforcement.yml
@@ -44,7 +44,13 @@ jobs:
           if test -s trusted-report.json; then
             python3 scripts/ci/agent_completion_enforcement.py trusted-report.json .github/agent-lock/trusted-publishers.json "$head" "$PR" > enforcement-verdict.json
           else
-            printf '%s\n' '{"conclusion":"failure","reason":"missing_trusted_publication","details":{}}' > enforcement-verdict.json
+            # If the policy is unprovisioned (all allowlists empty), yield a neutral advisory
+            # rather than a hard failure so PRs are not blocked while the GitHub App is not yet configured.
+            if python3 scripts/ci/agent_completion_enforcement.py --check-provisioned .github/agent-lock/trusted-publishers.json; then
+              printf '%s\n' '{"conclusion":"failure","reason":"missing_trusted_publication","details":{}}' > enforcement-verdict.json
+            else
+              printf '%s\n' '{"conclusion":"neutral","reason":"trust_policy_unprovisioned","details":{}}' > enforcement-verdict.json
+            fi
           fi
       - name: Publish the required head-bound Check run
         if: always()
@@ -71,9 +77,22 @@ jobs:
             } catch (error) {
               core.warning(error.message);
             }
-            const conclusion = verdict.conclusion === 'success'
-              ? 'success'
-              : 'failure';
+            let conclusion;
+            if (verdict.conclusion === 'success') {
+              conclusion = 'success';
+            } else if (verdict.conclusion === 'neutral') {
+              conclusion = 'neutral';
+            } else {
+              conclusion = 'failure';
+            }
+            let title;
+            if (conclusion === 'success') {
+              title = 'Trusted evidence verified';
+            } else if (conclusion === 'neutral') {
+              title = 'Trusted publisher not yet configured (advisory)';
+            } else {
+              title = 'Trusted evidence blocked';
+            }
             const summary = JSON.stringify(verdict);
             await github.rest.checks.create({
               owner: context.repo.owner,
@@ -83,12 +102,10 @@ jobs:
               status: 'completed',
               conclusion,
               output: {
-                title: conclusion === 'success'
-                  ? 'Trusted evidence verified'
-                  : 'Trusted evidence blocked',
+                title,
                 summary: summary.slice(0, 60000)
               }
             });
-            if (conclusion !== 'success') {
+            if (conclusion !== 'success' && conclusion !== 'neutral') {
               core.setFailed(verdict.reason || 'trusted evidence blocked');
             }
diff --git a/scripts/ci/agent_completion_enforcement.py b/scripts/ci/agent_completion_enforcement.py
index f746c6f20..09293c4c1 100644
--- a/scripts/ci/agent_completion_enforcement.py
+++ b/scripts/ci/agent_completion_enforcement.py
@@ -21,6 +21,25 @@ def verdict(reason: str, **details: Any) -> dict[str, Any]:
     return {"conclusion": "failure", "reason": reason, "details": details}
 
 
+def neutral_verdict(reason: str, **details: Any) -> dict[str, Any]:
+    return {"conclusion": "neutral", "reason": reason, "details": details}
+
+
+def is_provisioned(policy: Any) -> bool:
+    """Return True only when all three allowlists are non-empty.
+
+    The three required allowlists are trusted_check_app_slugs,
+    trusted_label_actors, and trusted_human_exemption_actors.
+    """
+    if not isinstance(policy, dict):
+        return False
+    return bool(
+        policy.get("trusted_check_app_slugs") and
+        policy.get("trusted_label_actors") and
+        policy.get("trusted_human_exemption_actors")
+    )
+
+
 def verify(payload: Any, policy: Any, head_sha: str, pull_number: int) -> dict[str, Any]:
     if not isinstance(payload, dict) or not isinstance(policy, dict):
         return verdict("invalid_payload")
@@ -34,8 +53,8 @@ def verify(payload: Any, policy: Any, head_sha: str, pull_number: int) -> dict[s
     if not all(isinstance(value, list) and all(isinstance(item, str) and item for item in value)
                    for value in (apps, labels, exemptions)):
         return verdict("invalid_trust_policy")
-    if not apps or not labels or not exemptions:
-        return verdict("trust_policy_unprovisioned")
+    if not is_provisioned(policy):
+        return neutral_verdict("trust_policy_unprovisioned")
     required = {"schema_version", "pull_number", "head_sha", "publisher", "applicability", "label_authorization", "focused_tests", "agent_events"}
     if set(payload) != required or payload.get("schema_version") != 1:
         return verdict("invalid_report_schema")
@@ -78,8 +97,13 @@ def verify(payload: Any, policy: Any, head_sha: str, pull_number: int) -> dict[s
 
 
 def main() -> int:
+    if len(sys.argv) == 3 and sys.argv[1] == "--check-provisioned":
+        policy_path = sys.argv[2]
+        provisioned = is_provisioned(json.loads(Path(policy_path).read_text()))
+        return 0 if provisioned else 1
     if len(sys.argv) != 5:
-        raise SystemExit("usage: verifier REPORT POLICY HEAD_SHA PULL_NUMBER")
+        raise SystemExit("usage: verifier REPORT POLICY HEAD_SHA PULL_NUMBER\n"
+                         "       verifier --check-provisioned POLICY")
     report, policy, head, pull = sys.argv[1:]
     result = verify(json.loads(Path(report).read_text()), json.loads(Path(policy).read_text()), head, int(pull))
     print(json.dumps(result, sort_keys=True))
diff --git a/tests/unit/test_agent_completion_enforcement.py b/tests/unit/test_agent_completion_enforcement.py
index 722a5cdd8..c37e1a7ca 100644
--- a/tests/unit/test_agent_completion_enforcement.py
+++ b/tests/unit/test_agent_completion_enforcement.py
@@ -17,7 +17,9 @@ def test_accepts_head_bound_trusted_report(self):
 
     def test_unprovisioned_policy_blocks(self):
         policy = dict(POLICY, trusted_check_app_slugs=[])
-        self.assertEqual(verify(report(), policy, HEAD, 9)["reason"], "trust_policy_unprovisioned")
+        result = verify(report(), policy, HEAD, 9)
+        self.assertEqual(result["reason"], "trust_policy_unprovisioned")
+        self.assertEqual(result["conclusion"], "neutral")
 
     def test_stale_report_blocks(self):
         body = report(); body["head_sha"] = "b" * 40