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.
This commit is contained in:
2026-05-02 18:07:57 -04:00
parent d1c4a48963
commit 999d3494b4
10 changed files with 272 additions and 1 deletions

View File

@@ -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),
},