feat(compliance-check): integrate banner cross-check + extract to module
Build + Deploy / build-admin-compliance (push) Successful in 1m57s
Build + Deploy / build-backend-compliance (push) Successful in 3m20s
Build + Deploy / build-ai-sdk (push) Successful in 48s
Build + Deploy / build-developer-portal (push) Successful in 1m6s
Build + Deploy / build-tts (push) Successful in 1m43s
Build + Deploy / build-document-crawler (push) Successful in 44s
Build + Deploy / build-dsms-gateway (push) Successful in 31s
Build + Deploy / build-dsms-node (push) Successful in 18s
CI / branch-name (push) Has been skipped
CI / guardrail-integrity (push) Has been skipped
CI / loc-budget (push) Failing after 16s
CI / secret-scan (push) Has been skipped
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / nodejs-build (push) Successful in 2m40s
CI / dep-audit (push) Has been skipped
CI / sbom-scan (push) Has been skipped
CI / test-go (push) Successful in 47s
CI / test-python-backend (push) Successful in 38s
CI / test-python-document-crawler (push) Successful in 28s
CI / test-python-dsms-gateway (push) Successful in 20s
CI / validate-canonical-controls (push) Successful in 14s
Build + Deploy / trigger-orca (push) Successful in 3m26s

Add automatic banner check (Step 3b) and banner-vs-cookie cross-check
(Step 3c) to unified compliance check. Extract cross-check logic to
banner_cookie_cross_check.py to keep routes under 500 LOC.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Benjamin Admin
2026-05-12 00:08:47 +02:00
parent 66d30568e2
commit b6ad958b69
2 changed files with 192 additions and 0 deletions
@@ -203,6 +203,44 @@ async def _run_compliance_check(check_id: str, req: ComplianceCheckRequest):
results.append(result)
total_findings += result.findings_count
# Step 3b: Banner-Check (automatic, uses first URL or homepage)
banner_result = None
banner_url = req.documents[0].url if req.documents and req.documents[0].url else ""
# Use the homepage (strip path) for banner check
if banner_url:
from urllib.parse import urlparse
parsed = urlparse(banner_url)
banner_url = f"{parsed.scheme}://{parsed.netloc}"
if banner_url:
_update(check_id, "Cookie-Banner wird geprueft...")
try:
async with httpx.AsyncClient(timeout=120.0) as client:
resp = await client.post(
f"{CONSENT_TESTER_URL}/scan",
json={"url": banner_url, "timeout_per_phase": 10},
)
if resp.status_code == 200:
banner_result = resp.json()
except Exception as e:
logger.warning("Banner check failed: %s", e)
# Step 3c: Cross-check Banner vs Cookie-Richtlinie
if banner_result and "cookie" in doc_texts:
_update(check_id, "Banner vs. Cookie-Richtlinie abgleichen...")
cross_findings = _cross_check_banner_vs_cookie(
banner_result, doc_texts["cookie"],
)
if cross_findings:
# Add cross-check findings to cookie results
for r in results:
if r.doc_type == "cookie":
for cf in cross_findings:
r.checks.append(CheckItem(**cf))
# Recompute
l2 = [c for c in r.checks if c.level == 2 and not c.skipped]
l2p = sum(1 for c in l2 if c.passed)
r.correctness_pct = round(l2p / len(l2) * 100) if l2 else 0
# Step 4: Build report
_update(check_id, "Report wird erstellt...")
report_html = build_html_report(results, None)
@@ -223,6 +261,11 @@ async def _run_compliance_check(check_id: str, req: ComplianceCheckRequest):
response = {
"results": [_result_to_dict(r) for r in results],
"business_profile": profile_dict,
"banner_result": {
"detected": banner_result.get("banner_detected", False) if banner_result else False,
"provider": banner_result.get("banner_provider", "") if banner_result else "",
"violations": len(banner_result.get("banner_checks", {}).get("violations", [])) if banner_result else 0,
} if banner_result else None,
"total_documents": len(results),
"total_findings": total_findings,
"email_status": email_result.get("status", "failed"),
@@ -437,3 +480,7 @@ def _build_profile_html(profile) -> str:
f'<td>{int(profile.confidence * 100)}%</td></tr>'
'</table></div>'
)
# Cross-check extracted to compliance.services.banner_cookie_cross_check
from compliance.services.banner_cookie_cross_check import cross_check_banner_vs_cookie as _cross_check_banner_vs_cookie
@@ -0,0 +1,145 @@
"""
Banner ↔ Cookie-Richtlinie Cross-Check.
Compares what the cookie banner actually does (Playwright scan)
with what the cookie policy text promises. Finds mismatches:
- Services used but not documented
- Tracking before consent despite claiming consent-only
- False "no tracking" claims contradicted by actual cookies
"""
import logging
import re
logger = logging.getLogger(__name__)
def cross_check_banner_vs_cookie(
banner_result: dict,
cookie_text: str,
) -> list[dict]:
"""Cross-check: Does the banner behavior match the cookie policy text?
Returns list of CheckItem-compatible dicts for mismatches.
"""
findings: list[dict] = []
cookie_lower = cookie_text.lower()
phases = banner_result.get("phases", {})
before = phases.get("before_consent", {})
after_accept = phases.get("after_accept", {})
# 1. Services found by banner but not mentioned in cookie policy
tracking_before = before.get("tracking_services", [])
all_tracking = set(tracking_before)
for s in after_accept.get("tracking_services", []):
if isinstance(s, str):
all_tracking.add(s)
for service in all_tracking:
service_lower = service.lower()
mentioned = any(kw in cookie_lower for kw in [
service_lower,
service_lower.replace(" ", ""),
service_lower.split()[0] if " " in service_lower else service_lower,
])
if not mentioned:
findings.append({
"id": f"cross-{service_lower.replace(' ', '_')[:20]}",
"label": f"Dienst '{service}' fehlt in Cookie-Richtlinie",
"passed": False,
"severity": "HIGH",
"level": 2,
"parent": None,
"skipped": False,
"matched_text": "",
"hint": (
f"Der Banner-Scan hat '{service}' auf der Website erkannt, "
f"aber die Cookie-Richtlinie erwaehnt diesen Dienst nicht. "
f"Gemaess Art. 13(1)(e) DSGVO muessen alle Empfaenger/"
f"Dienste in der DSI benannt werden."
),
"source": "cross_check",
})
# 2. Tracking before consent but cookie policy says "nur mit Einwilligung"
if tracking_before:
consent_words = re.findall(
r"(?:einwilligung|consent|zustimmung).*?"
r"(?:erforderlich|notwendig|vorher|vorab)",
cookie_lower,
)
if consent_words:
findings.append({
"id": "cross-tracking-before-consent",
"label": "Tracking vor Consent trotz Einwilligungspflicht",
"passed": False,
"severity": "CRITICAL",
"level": 2,
"parent": None,
"skipped": False,
"matched_text": ", ".join(tracking_before[:3]),
"hint": (
f"Die Cookie-Richtlinie spricht von Einwilligungspflicht, "
f"aber der Banner-Scan hat {len(tracking_before)} Tracking-"
f"Dienst(e) VOR Consent erkannt: {', '.join(tracking_before[:3])}. "
f"Dies ist ein Verstoss gegen §25 Abs. 1 TDDDG."
),
"source": "cross_check",
})
# 3. Banner sets tracking cookies but policy claims "no tracking"
accept_cookies = after_accept.get("cookies", [])
tracking_prefixes = ("_ga", "_gid", "_fbp", "_fbc", "IDE", "_gcl",
"fr", "_pin", "_tt_", "li_sugr", "_hj")
tracking_cookies = [c for c in accept_cookies
if any(c.startswith(p) for p in tracking_prefixes)]
if tracking_cookies:
no_tracking_claim = any(kw in cookie_lower for kw in [
"keine tracking", "kein tracking", "keine marketing",
"keine werbe", "no tracking",
])
if no_tracking_claim:
findings.append({
"id": "cross-false-no-tracking",
"label": "Cookie-Richtlinie behauptet 'kein Tracking'"
"Banner widerspricht",
"passed": False,
"severity": "CRITICAL",
"level": 2,
"parent": None,
"skipped": False,
"matched_text": ", ".join(tracking_cookies[:5]),
"hint": (
f"Die Cookie-Richtlinie behauptet kein Tracking, aber "
f"nach Akzeptieren wurden Tracking-Cookies gesetzt: "
f"{', '.join(tracking_cookies[:5])}. "
f"Transparenzverstoss nach Art. 5(1)(a) DSGVO."
),
"source": "cross_check",
})
# 4. Banner detected but no cookie policy provided
banner_detected = banner_result.get("banner_detected", False)
if banner_detected and len(cookie_lower.strip()) < 100:
findings.append({
"id": "cross-banner-no-policy",
"label": "Cookie-Banner vorhanden aber keine Cookie-Richtlinie",
"passed": False,
"severity": "HIGH",
"level": 2,
"parent": None,
"skipped": False,
"matched_text": "",
"hint": (
"Die Website zeigt ein Cookie-Banner, aber es wurde keine "
"Cookie-Richtlinie eingereicht. Eine separate Cookie-Richtlinie "
"oder ein Cookie-Abschnitt in der DSI ist nach §25 TDDDG "
"erforderlich wenn nicht-essentielle Cookies verwendet werden."
),
"source": "cross_check",
})
logger.info("Cross-check: %d findings (%d services, %d tracking before)",
len(findings), len(all_tracking), len(tracking_before))
return findings