feat(privacy): scan ingested sources for customer-identifying data

Detection-only scan (internal/privacy) attached to every AnalysisResult:
a customer-domain guess plus a findings list (category, file, line, match,
hint), ported from the KB grep playbook. Runs on archive uploads and the
serialized Redfish tree; gated by LOGPILE_PRIVACY_SCAN (default on).

Surfaced at GET /api/privacy-scan, in the "Customer data" UI panel, and as
privacy_report.json in the raw-export bundle. IP policy keeps RFC1918 and
example ranges out of findings; allowlist covers standards-body and vendor
infrastructure domains. No customer tokens in the repo. See ADL-066 and
bible-local/docs/privacy-scan.md.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This commit is contained in:
Mikhail Chusavitin
2026-09-02 15:24:32 +03:00
co-authored by Claude Sonnet 5
parent 3311bafd8e
commit 4a4910f207
23 changed files with 1466 additions and 33 deletions
+59
View File
@@ -0,0 +1,59 @@
package privacy
import "net"
// Documentation, benchmarking, and well-known example addresses that carry no
// site information even though they are globally routable.
var nonSensitiveNets = func() []*net.IPNet {
cidrs := []string{
"192.0.2.0/24", // RFC 5737 TEST-NET-1
"198.51.100.0/24", // RFC 5737 TEST-NET-2
"203.0.113.0/24", // RFC 5737 TEST-NET-3
"198.18.0.0/15", // RFC 2544 benchmarking
"100.64.0.0/10", // RFC 6598 CGNAT
"192.88.99.0/24", // RFC 7526 6to4 relay anycast
}
out := make([]*net.IPNet, 0, len(cidrs))
for _, c := range cidrs {
if _, n, err := net.ParseCIDR(c); err == nil {
out = append(out, n)
}
}
return out
}()
var nonSensitiveExact = map[string]struct{}{
"8.8.8.8": {}, "8.8.4.4": {}, "1.1.1.1": {}, "1.0.0.1": {},
"4.2.2.2": {}, "4.2.2.1": {}, "9.9.9.9": {}, "1.2.3.4": {},
"208.67.222.222": {}, "208.67.220.220": {},
}
// isSensitiveIP reports whether s is a routable address that could identify the
// customer's provider or site. Private (RFC1918/ULA), loopback, link-local,
// multicast, and the example/benchmark ranges above are not sensitive.
func isSensitiveIP(s string) bool {
ip := net.ParseIP(s)
if ip == nil {
return false
}
if _, ok := nonSensitiveExact[s]; ok {
return false
}
if ip.IsLoopback() || ip.IsPrivate() || ip.IsUnspecified() ||
ip.IsLinkLocalUnicast() || ip.IsLinkLocalMulticast() ||
ip.IsMulticast() || ip.IsInterfaceLocalMulticast() {
return false
}
if !ip.IsGlobalUnicast() {
return false
}
if v4 := ip.To4(); v4 != nil && (v4[0] == 0 || v4[0] == 255 || v4[0] >= 240) {
return false
}
for _, n := range nonSensitiveNets {
if n.Contains(ip) {
return false
}
}
return true
}