Add suspicious-signup sweep: suspend flagged signups with no activity
Watches every account flagged by IP-scrutiny or email-domain scrutiny at signup and, once it goes live, records a baseline post/follow count. A scheduled sweep (app/suspicious_sweep.py, run via cron on admin.yttrx.com) suspends any watch past SUSPICIOUS_GRACE_HOURS with zero new posts and zero new follows since that baseline; any activity clears the watch. Works whether yttrx is open-registration or requires moderator approval, since the watch starts at whichever event actually makes the account live (account.created vs account.approved), same dual handling the welcome flow already uses. Needs ABUSE_BOT_TOKEN re-minted with admin:read:accounts.
This commit is contained in:
+105
-2
@@ -170,6 +170,29 @@ CHECK_MAIL_HOLD_WELCOME = os.environ.get("CHECK_MAIL_HOLD_WELCOME", "true").lowe
|
||||
# Admin::EmailDomainBlock (blocks future signups from that domain).
|
||||
CHECK_MAIL_AUTO_DOMAIN_BLOCK = os.environ.get("CHECK_MAIL_AUTO_DOMAIN_BLOCK", "true").lower() in ("1", "true", "yes")
|
||||
|
||||
# --- Suspicious-signup sweep (flagged at signup, no activity in grace window) ---
|
||||
# Watches every account flagged by EITHER IP-scrutiny or email-domain scrutiny
|
||||
# at signup. Once the account goes live — account.created if signups are open
|
||||
# (or an already-approved account), account.approved if this instance requires
|
||||
# moderator approval, same dual event handling the welcome flow already uses —
|
||||
# a baseline post/follow count is recorded (see maybe_start_suspicious_watch).
|
||||
# A separate scheduled job (bin/welcomebot-suspicious sweep, see CLAUDE.md) run
|
||||
# via `python -m app.suspicious_sweep` looks for accounts past
|
||||
# SUSPICIOUS_GRACE_HOURS with zero new posts AND zero new follows since that
|
||||
# baseline, and takes SUSPICIOUS_ACTION on them.
|
||||
SUSPICIOUS_SWEEP_ENABLED = os.environ.get("SUSPICIOUS_SWEEP_ENABLED", "true").lower() in ("1", "true", "yes")
|
||||
# Hours of grace given to a flagged signup to show organic activity (a new
|
||||
# post or a new follow) before it's considered dormant/bot-like.
|
||||
SUSPICIOUS_GRACE_HOURS = int(os.environ.get("SUSPICIOUS_GRACE_HOURS", "24"))
|
||||
# "suspend" (agreed default — a flagged signup with zero organic activity in
|
||||
# the grace window is a strong bulk/bot-signup signal, stronger than the
|
||||
# report-driven abuse-bot's default "silence") or "silence".
|
||||
SUSPICIOUS_ACTION = os.environ.get("SUSPICIOUS_ACTION", "suspend").lower()
|
||||
# Rollout safety switch, same role as ABUSE_DRY_RUN — ships "false" (live)
|
||||
# here per an explicit decision to skip the usual dry-run rollout step for
|
||||
# this feature. Flip to "true" to pause without redeploying.
|
||||
SUSPICIOUS_DRY_RUN = os.environ.get("SUSPICIOUS_DRY_RUN", "false").lower() in ("1", "true", "yes")
|
||||
|
||||
if not WEBHOOK_SECRET:
|
||||
log.warning("WEBHOOK_SECRET is empty — signature verification will reject all requests.")
|
||||
if not BOT_ACCESS_TOKEN:
|
||||
@@ -248,6 +271,18 @@ def _init_db() -> None:
|
||||
" cached_at TEXT DEFAULT CURRENT_TIMESTAMP"
|
||||
")"
|
||||
)
|
||||
conn.execute(
|
||||
"CREATE TABLE IF NOT EXISTS suspicious_watch ("
|
||||
" account_id TEXT PRIMARY KEY,"
|
||||
" acct TEXT,"
|
||||
" reasons TEXT,"
|
||||
" started_at TEXT DEFAULT CURRENT_TIMESTAMP,"
|
||||
" baseline_statuses_count INTEGER,"
|
||||
" baseline_following_count INTEGER,"
|
||||
" status TEXT DEFAULT 'pending',"
|
||||
" resolved_at TEXT"
|
||||
")"
|
||||
)
|
||||
|
||||
|
||||
@contextmanager
|
||||
@@ -387,6 +422,25 @@ def cache_check_mail(domain: str, is_disposable: bool, risk: int) -> None:
|
||||
)
|
||||
|
||||
|
||||
def already_watched_suspicious(account_id: str) -> bool:
|
||||
with _db() as conn:
|
||||
row = conn.execute(
|
||||
"SELECT 1 FROM suspicious_watch WHERE account_id = ?", (account_id,)
|
||||
).fetchone()
|
||||
return row is not None
|
||||
|
||||
|
||||
def start_suspicious_watch(account_id: str, acct: str, reasons: str,
|
||||
statuses_count: int, following_count: int) -> None:
|
||||
with _db() as conn:
|
||||
conn.execute(
|
||||
"INSERT OR IGNORE INTO suspicious_watch "
|
||||
"(account_id, acct, reasons, baseline_statuses_count, baseline_following_count) "
|
||||
"VALUES (?, ?, ?, ?, ?)",
|
||||
(account_id, acct, reasons, statuses_count, following_count),
|
||||
)
|
||||
|
||||
|
||||
_init_db()
|
||||
|
||||
# --- Signature verification ------------------------------------------------
|
||||
@@ -542,7 +596,51 @@ def process_signup(account_id: str, acct: str, ip: str, email: str = "") -> None
|
||||
|
||||
if not hold:
|
||||
send_welcome(account_id, acct)
|
||||
# else: held — sent later if/when account.approved fires (human review).
|
||||
maybe_start_suspicious_watch(account_id, acct)
|
||||
# else: held — sent later if/when account.approved fires (human review),
|
||||
# which is also where maybe_start_suspicious_watch gets called.
|
||||
|
||||
|
||||
def maybe_start_suspicious_watch(account_id: str, acct: str) -> None:
|
||||
"""Start the suspicious-sweep grace-period clock for a flagged signup.
|
||||
|
||||
Called at the moment the account actually goes live — immediately in
|
||||
process_signup() when the welcome isn't held, or from the
|
||||
account.approved handler once a human clears the approval queue for a
|
||||
held one. Either path is a no-op if the account was never flagged (by
|
||||
IP-scrutiny or email-domain scrutiny) or is already being watched, so
|
||||
it's safe to call from both places unconditionally.
|
||||
"""
|
||||
if not SUSPICIOUS_SWEEP_ENABLED or already_watched_suspicious(account_id):
|
||||
return
|
||||
|
||||
ip_flagged = get_signup_flag(account_id)
|
||||
_, email_flagged = get_signup_email(account_id)
|
||||
if not (ip_flagged or email_flagged):
|
||||
return
|
||||
|
||||
reasons = ",".join(
|
||||
r for r, flagged in (("ip", ip_flagged), ("email", email_flagged)) if flagged
|
||||
)
|
||||
try:
|
||||
statuses_count, following_count = fetch_account_counts(account_id)
|
||||
except httpx.HTTPError as exc:
|
||||
log.error("failed to snapshot suspicious-watch baseline for acct=%s: %s", acct, exc)
|
||||
return
|
||||
|
||||
start_suspicious_watch(account_id, acct, reasons, statuses_count, following_count)
|
||||
log.info("started suspicious watch acct=%s reasons=%s baseline=(statuses=%d, following=%d)",
|
||||
acct, reasons, statuses_count, following_count)
|
||||
|
||||
|
||||
def fetch_account_counts(account_id: str) -> tuple[int, int]:
|
||||
"""Return (statuses_count, following_count) for an account via the public
|
||||
account API. Split out from maybe_start_suspicious_watch as a single seam
|
||||
to stub in tests."""
|
||||
resp = httpx.get(f"{MASTODON_BASE_URL}/api/v1/accounts/{account_id}", timeout=15.0)
|
||||
resp.raise_for_status()
|
||||
data = resp.json()
|
||||
return data.get("statuses_count", 0), data.get("following_count", 0)
|
||||
|
||||
|
||||
# --- Mastodon API (abuse) --------------------------------------------------
|
||||
@@ -945,8 +1043,13 @@ def _handle_account_created(obj: dict, background: BackgroundTasks, event: str):
|
||||
else:
|
||||
# account.approved: a human has cleared the approval-required
|
||||
# registration gate. Always welcome (dedup makes this safe) — this is
|
||||
# what lifts a held welcome for a previously-flagged signup.
|
||||
# what lifts a held welcome for a previously-flagged signup. Also the
|
||||
# moment a held, flagged signup's suspicious-watch clock should start;
|
||||
# a no-op if it was never flagged or already started (open-signup
|
||||
# case, where account.approved may fire right alongside
|
||||
# account.created).
|
||||
background.add_task(send_welcome, account_id, acct)
|
||||
background.add_task(maybe_start_suspicious_watch, account_id, acct)
|
||||
return {"ok": True, "queued": acct}
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user