diff --git a/pilot/ai_review.py b/pilot/ai_review.py
index 073da0e..37f5d50 100644
--- a/pilot/ai_review.py
+++ b/pilot/ai_review.py
@@ -102,7 +102,7 @@ Output STRICT JSON only — no prose, no markdown fences. Shape:
 {
   "findings": [
     {
-      "severity": "critical|high|medium|low",
+      "severity": "critical|high|medium|low|trivial|info",
       "path": "file path exactly as it appears in the diff (`+++ b/` side)",
       "line": <int, the NEW-file line number the issue is on, within the diff>,
       "problem": "one line: what is wrong",
@@ -963,12 +963,19 @@ _SEVERITY_EMOJI = {
     "nit": "⚪",
 }
 
+# Severities whose own name is rendered verbatim (uppercased) in the badge.
+# Anything outside this set falls back to "INFO" so the badge label stays
+# a clean short token regardless of what the model emits.
+_BADGED_SEVERITY_LABELS = frozenset({
+    "critical", "high", "medium", "low", "trivial", "info", "nit",
+})
+
 
 def _severity_badge(severity: str) -> str:
     """Render the severity as emoji + uppercase label (e.g. ``🔴 [HIGH]``)."""
     sev = (severity or "").lower()
     emoji = _SEVERITY_EMOJI.get(sev, "⚪")
-    label = sev.upper() if sev in {"critical", "high", "medium", "low"} else "INFO"
+    label = sev.upper() if sev in _BADGED_SEVERITY_LABELS else "INFO"
     return f"{emoji} [{label}]"
 
 
diff --git a/tests/pilot/test_ai_review.py b/tests/pilot/test_ai_review.py
index 3ab2231..d5e02dd 100644
--- a/tests/pilot/test_ai_review.py
+++ b/tests/pilot/test_ai_review.py
@@ -17,6 +17,7 @@ from ai_review import (  # noqa: E402
     _last_balanced_json,
     _normalize_finding,
     _render_collapsible_usage,
+    _severity_badge,
     build_user_prompt,
     compute_attribution,
     findings_table,
@@ -321,7 +322,7 @@ def test_inline_comment_body_severity_emoji_mapping():
         ("medium", "🟡 [MEDIUM]"),
         ("low", "🔵 [LOW]"),
         ("info", "⚪ [INFO]"),
-        ("nit", "⚪ [INFO]"),  # "nit" maps to the INFO label
+        ("nit", "⚪ [NIT]"),  # legacy alias — renders with its own name
         ("bogus", "⚪ [INFO]"),  # unknown severity falls back to INFO
     ]
     for sev, badge in cases:
@@ -1746,3 +1747,11 @@ def test_emoji_for_trivial_and_info_is_neutral():
     assert _SEVERITY_EMOJI["trivial"] == "⚪"
     assert _SEVERITY_EMOJI["info"] == "⚪"
 
+
+def test_severity_badge_labels_each_known_severity():
+    # Trivial and info (and legacy nit) should render with their own name,
+    # not fall back to "INFO".
+    for sev in ("critical", "high", "medium", "low", "trivial", "info", "nit"):
+        badge = _severity_badge(sev)
+        assert f"[{sev.upper()}]" in badge, (sev, badge)
+