diff --git a/app/services/output_review.py b/app/services/output_review.py
index 401096d..833b927 100644
--- a/app/services/output_review.py
+++ b/app/services/output_review.py
@@ -60,7 +60,22 @@ Mark UNCLEAN if the text contains ANY of:
 - Partial / truncated content. Starts mid-word, mid-number, mid-clause.
 - Visible internal numbers without clear meaning ("change 1y +5.9%?"),
   raw column names ("as_of 2026-01-01"), or any debug-like fragments.
-- Anything other than the finished, publishable interpretation.
+- FINANCIAL ADVICE or any phrasing that recommends an action the
+  reader should take. This service is editorial commentary on public
+  data, not investment advice; the operator is not licensed to give
+  it. Reject any of:
+    * Buy/sell/hold/accumulate/trim/exit/enter/rotate language.
+    * Allocation guidance ("overweight", "underweight",
+      "X% in bonds", "increase exposure to").
+    * Price targets or specific level predictions ("will reach $X",
+      "target Y", "expect Z by year-end").
+    * Personalised framing ("you should", "investors should",
+      "consider buying", "we recommend").
+  DESCRIPTIVE / INTERPRETIVE language about market state is fine —
+  "valuations are stretched", "real yields are restrictive", "rates
+  and credit disagree". The test: does the text describe a STATE, or
+  does it suggest an ACTION? States are fine; actions are not.
+- Anything else other than the finished, publishable interpretation.
 
 Return ONLY a JSON object with this exact shape:
 {"clean": true | false, "reason": "<≤20 words, plain text>"}