feat(intel): persist per-provider taxonomy on AttackerIntel for TTP dispatch

The 2026-05-02 ship-time audit of the R0054-R0058 intel rule pack found
that AbuseIPDB / GreyNoise / ThreatFox stored only the aggregate verdict
(score / classification / listed-bool) plus the raw response blob. The
TTP IntelLifter expects per-provider taxonomy fields (categories, tags,
threat_types) that were never populated, so R0054 / R0055 / R0057
emitted zero tags in production despite passing unit tests.

Add typed columns: abuseipdb_categories, greynoise_tags, greynoise_name,
feodo_malware_family, threatfox_threat_types, threatfox_ioc_types,
threatfox_malware_families. Each provider now parses the relevant
taxonomy out of the upstream response and writes it through
column_updates. JSON-list columns ride as TEXT with default "[]" to
keep the SQLite/MySQL backend split honest, deserialised back to native
lists by the repo on read.

decnet/intel/abuseipdb.py

@@ -93,11 +93,24 @@ class AbuseIPDBProvider(IntelProvider):
         data = payload.get("data") or {}
         score = int(data.get("abuseConfidenceScore") or 0)
         verdict = _score_to_verdict(score)
+        # AbuseIPDB returns ``data.reports[*].categories`` — a list of
+        # int codes per report. Flatten the union across all recent
+        # reports so the IntelLifter sees the full activity profile,
+        # not just the most-recent report's categories. Sorted for
+        # determinism (matters for tests + for the bus payload diff).
+        categories: set[int] = set()
+        for report in data.get("reports") or []:
+            if not isinstance(report, dict):
+                continue
+            for cat in report.get("categories") or []:
+                if isinstance(cat, int):
+                    categories.add(cat)
         return IntelResult(
             provider=self.name,
             verdict=verdict,
             column_updates={
                 "abuseipdb_score": score,
+                "abuseipdb_categories": json.dumps(sorted(categories)),
                 "abuseipdb_raw": json.dumps(data),
                 "abuseipdb_queried_at": datetime.now(timezone.utc),
             },

decnet/intel/feodo.py

@@ -93,15 +93,21 @@ class FeodoProvider(IntelProvider):
                 verdict=None,  # absence ≠ "benign", let other providers speak
                 column_updates={
                     "feodo_listed": False,
+                    "feodo_malware_family": None,
                     "feodo_raw": "{}",
                     "feodo_queried_at": datetime.now(timezone.utc),
                 },
             )
+        family_obj = entry.get("malware")
+        family = (
+            family_obj if isinstance(family_obj, str) and family_obj else None
+        )
         return IntelResult(
             provider=self.name,
             verdict="malicious",
             column_updates={
                 "feodo_listed": True,
+                "feodo_malware_family": family,
                 "feodo_raw": json.dumps(entry),
                 "feodo_queried_at": datetime.now(timezone.utc),
             },

decnet/intel/greynoise.py

@@ -71,6 +71,8 @@ class GreyNoiseProvider(IntelProvider):
                 verdict="unknown",
                 column_updates={
                     "greynoise_classification": "unknown",
+                    "greynoise_name": None,
+                    "greynoise_tags": "[]",
                     "greynoise_raw": json.dumps({"message": "not seen"}),
                     "greynoise_queried_at": datetime.now(timezone.utc),
                 },
@@ -88,11 +90,24 @@ class GreyNoiseProvider(IntelProvider):
 
         classification = (data.get("classification") or "unknown").lower()
         verdict = _CLASSIFICATION_TO_VERDICT.get(classification, "unknown")
+        # The Community endpoint surfaces an actor ``name`` (e.g. "Tor",
+        # "Censys") but no behavioral tag list — the tag taxonomy is
+        # paid-tier only. Persist whatever we got; a future non-Community
+        # provider may populate ``greynoise_tags``.
+        name_obj = data.get("name")
+        name = name_obj if isinstance(name_obj, str) and name_obj else None
+        tags_obj = data.get("tags")
+        tags: list[str] = (
+            [t for t in tags_obj if isinstance(t, str)]
+            if isinstance(tags_obj, list) else []
+        )
         return IntelResult(
             provider=self.name,
             verdict=verdict,
             column_updates={
                 "greynoise_classification": classification,
+                "greynoise_name": name,
+                "greynoise_tags": json.dumps(tags),
                 "greynoise_raw": json.dumps(data),
                 "greynoise_queried_at": datetime.now(timezone.utc),
             },

decnet/intel/threatfox.py

@@ -71,6 +71,9 @@ class ThreatFoxProvider(IntelProvider):
                 verdict=None,  # absence is not a benign signal
                 column_updates={
                     "threatfox_listed": False,
+                    "threatfox_threat_types": "[]",
+                    "threatfox_ioc_types": "[]",
+                    "threatfox_malware_families": "[]",
                     "threatfox_raw": "{}",
                     "threatfox_queried_at": datetime.now(timezone.utc),
                 },
@@ -83,11 +86,36 @@ class ThreatFoxProvider(IntelProvider):
 
         data = payload.get("data") or []
         listed = bool(data)
+        # Each match in ``data`` carries threat_type / ioc_type / malware
+        # (canonical family). The IntelLifter dispatches ATT&CK techniques
+        # off ``threat_type`` (botnet_cc / payload_delivery / payload /
+        # cc_skimming); the other two columns are evidence and SIEM
+        # context. Sets are flattened across matches and serialised
+        # sorted for determinism.
+        threat_types: set[str] = set()
+        ioc_types: set[str] = set()
+        families: set[str] = set()
+        if isinstance(data, list):
+            for entry in data:
+                if not isinstance(entry, dict):
+                    continue
+                tt = entry.get("threat_type")
+                if isinstance(tt, str) and tt:
+                    threat_types.add(tt)
+                it = entry.get("ioc_type")
+                if isinstance(it, str) and it:
+                    ioc_types.add(it)
+                family = entry.get("malware") or entry.get("malware_printable")
+                if isinstance(family, str) and family:
+                    families.add(family)
         return IntelResult(
             provider=self.name,
             verdict="malicious" if listed else None,
             column_updates={
                 "threatfox_listed": listed,
+                "threatfox_threat_types": json.dumps(sorted(threat_types)),
+                "threatfox_ioc_types": json.dumps(sorted(ioc_types)),
+                "threatfox_malware_families": json.dumps(sorted(families)),
                 "threatfox_raw": json.dumps(data),
                 "threatfox_queried_at": datetime.now(timezone.utc),
             },