diff --git a/tools/observer-classification-map.json b/tools/observer-classification-map.json
index c281856a..63166eb3 100644
--- a/tools/observer-classification-map.json
+++ b/tools/observer-classification-map.json
@@ -1,6 +1,6 @@
 {
   "$schema_version": 1,
-  "description": "Mapping from observer transcript-parser task_classification values to recommended Tooling Прил.Н node IDs. Source of truth for missed-activation detection (Pravila §16.4 conditional rule). 'other' deliberately empty — no recommendation, never counts as missed. DEFERRED-узлы filtered out by .node-dormancy.json at runtime.",
+  "description": "Mapping from observer transcript-parser task_classification values to recommended Tooling Прил.Н node IDs. Source of truth for missed-activation detection (Pravila §16.4 conditional rule). 'other' deliberately empty — no recommendation, never counts as missed. DEFERRED-узлы filtered out by .node-dormancy.json at runtime. Classifier vocabulary is Claude's free judgment when writing the episode (no hardcoded enum) — adding a key here makes it 'blessed'. 'security' added 22.05.2026 (A8 follow-up): use when the PURPOSE of the task is verifying or improving security (scans, hardening, audits, threat modeling, go-live gates); NOT for bug-fixes that happen to be in security-relevant code (those stay 'bugfix').",
   "map": {
     "refactor":     ["#11", "#12", "#43", "#64", "#65"],
     "bugfix":       ["#18", "#34"],
@@ -9,6 +9,7 @@
     "memory-sync":  ["#33"],
     "monitoring":   ["#34", "#35"],
     "analysis":     ["#25", "#39", "#53"],
+    "security":     ["#73", "#69", "#68", "#70", "#71", "#72"],
     "cleanup":      ["#11", "#12"],
     "question":     ["#60"],
     "other":        []