fix(bounties): strip per-request fields from fingerprint payloads
add_bounty dedups on (attacker_ip, bounty_type, full payload JSON).
Three fingerprint-family bounties (http_useragent, ip_leak,
http_quirks) were including method/path / header_count in their
payloads — fields that vary per request — so a scanner hitting 100
paths produced 100 rows instead of 1, which is what was swelling
AttackerDetail.
Payloads now carry identity-only fields:
- http_useragent: {fingerprint_type, value}. UA + path combinations
no longer collide; one row per distinct User-Agent string.
- ip_leak: {source_ip, real_ip_claim, source_header, headers_seen}.
One row per distinct (proxy source, leaked IP, leaking header)
triple; repeat hits with the same header on different paths dedup.
- http_quirks: {fingerprint_type, order_hash, order, casing_hash,
casing_category, stable_count, tool_guess}. No more header_count
(included volatile headers; Cookie-presence variance broke dedup).
Per-request context (path, method, etc.) was never load-bearing for
analysts — the logs table already answers "when + where" at
per-event resolution. The bounty table is for stable identity.
UI:
- FpHttpQuirks renderer drops the method/path footer line and the
header_count/duplicates tags; shows stable_count instead.
- LEAKED-IPs tooltip on AttackerDetail swaps "X on GET /path" for
"Leaked via X; source 203.0.113.42" — same information, stable.
Tests add a "payload stable across paths and methods" assertion on
http_quirks — locks the contract so a future regression that sneaks
a per-request field back in fails loudly.
Existing duplicate bounty rows don't retroactively collapse.
Dev: `decnet db-reset --i-know-what-im-doing drop-tables` and
restart. Prod: one SQL pass to dedup by (attacker_ip, bounty_type,
payload) — trivial but not automated.
This commit is contained in:
@@ -268,8 +268,9 @@ class TestGetAttackerDetail:
|
||||
"source_ip": "203.0.113.42",
|
||||
"real_ip_claim": "198.51.100.7",
|
||||
"source_header": "X-Forwarded-For",
|
||||
"path": "/wp-admin/",
|
||||
"method": "GET",
|
||||
"headers_seen": {
|
||||
"X-Forwarded-For": "198.51.100.7",
|
||||
},
|
||||
},
|
||||
},
|
||||
]
|
||||
|
||||
@@ -80,7 +80,9 @@ def test_different_casing_different_hash():
|
||||
|
||||
def test_volatile_headers_excluded_from_hash():
|
||||
"""Content-Length, Cookie, XFF etc. are per-request; the identity
|
||||
hash shouldn't depend on them."""
|
||||
hash must not depend on them, otherwise two requests from the same
|
||||
stack — one with Cookie, one without — would dedup-miss at the
|
||||
bounty layer and spam the AttackerDetail page."""
|
||||
row_a = _log_row({
|
||||
"Host": "x", "User-Agent": "a", "Content-Length": "100",
|
||||
})
|
||||
@@ -90,13 +92,11 @@ def test_volatile_headers_excluded_from_hash():
|
||||
})
|
||||
fa = _http_quirks_fingerprint(row_a, row_a["fields"]["headers"])
|
||||
fb = _http_quirks_fingerprint(row_b, row_b["fields"]["headers"])
|
||||
assert fa["order_hash"] == fb["order_hash"]
|
||||
# Count reflects ALL headers (the volatile ones WERE there).
|
||||
assert fa["header_count"] == 3
|
||||
assert fb["header_count"] == 4
|
||||
# Stable count excludes the volatile ones.
|
||||
# Whole payload must be identical — add_bounty dedups on the full
|
||||
# serialized payload, so ANY per-request-varying field would spawn
|
||||
# new rows. This assertion is the contract.
|
||||
assert fa == fb
|
||||
assert fa["stable_count"] == 2
|
||||
assert fb["stable_count"] == 2
|
||||
|
||||
|
||||
# ─── tool guesses ──────────────────────────────────────────────────────────
|
||||
@@ -148,11 +148,10 @@ def test_empty_headers_skipped():
|
||||
|
||||
def test_only_volatile_headers_still_emits():
|
||||
"""If every header is in the volatile set we still want a fingerprint,
|
||||
just with empty order — header count alone is still a signal."""
|
||||
just with empty order — "zero stable headers" is itself a signal."""
|
||||
row = _log_row({"Content-Length": "10", "Cookie": "a=b"})
|
||||
f = _http_quirks_fingerprint(row, row["fields"]["headers"])
|
||||
assert f is not None
|
||||
assert f["header_count"] == 2
|
||||
assert f["stable_count"] == 0
|
||||
assert f["order"] == []
|
||||
|
||||
@@ -198,6 +197,27 @@ async def test_extract_bounty_non_http_skips_quirks():
|
||||
assert payload.get("fingerprint_type") != "http_quirks"
|
||||
|
||||
|
||||
def test_payload_stable_across_paths_and_methods():
|
||||
"""Two requests from the same stack hitting different paths/methods
|
||||
must produce byte-identical payloads so (ip, type, payload) dedup
|
||||
collapses them into one bounty row. If this test breaks, check
|
||||
whether a per-request field snuck back into _http_quirks_fingerprint."""
|
||||
headers = {"Host": "target", "User-Agent": "curl/8.0", "Accept": "*/*"}
|
||||
row_get = {
|
||||
"decky": "http-01", "service": "http", "attacker_ip": "1.2.3.4",
|
||||
"event_type": "request",
|
||||
"fields": {"method": "GET", "path": "/admin", "headers": headers},
|
||||
}
|
||||
row_post = {
|
||||
"decky": "http-01", "service": "http", "attacker_ip": "1.2.3.4",
|
||||
"event_type": "request",
|
||||
"fields": {"method": "POST", "path": "/wp-login.php", "headers": headers},
|
||||
}
|
||||
fa = _http_quirks_fingerprint(row_get, headers)
|
||||
fb = _http_quirks_fingerprint(row_post, headers)
|
||||
assert fa == fb, "payload must not depend on request method/path"
|
||||
|
||||
|
||||
# ─── hash stability across restarts ─────────────────────────────────────────
|
||||
|
||||
def test_short_hash_deterministic():
|
||||
|
||||
@@ -39,7 +39,10 @@ def test_xff_leftmost_differs_from_source_emits_leak():
|
||||
assert result["source_ip"] == "203.0.113.42"
|
||||
assert result["real_ip_claim"] == "198.51.100.7"
|
||||
assert result["source_header"] == "X-Forwarded-For"
|
||||
assert result["path"] == "/wp-admin/"
|
||||
# Identity-only payload — method/path intentionally omitted so the
|
||||
# bounty dedup collapses repeat hits from the same attacker.
|
||||
assert "method" not in result
|
||||
assert "path" not in result
|
||||
|
||||
|
||||
def test_xff_matches_source_no_leak():
|
||||
|
||||
Reference in New Issue
Block a user