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
+27
View File
@@ -3,10 +3,12 @@ package parser
import (
"fmt"
"io"
"os"
"strings"
"time"
"git.mchus.pro/mchus/logpile/internal/models"
"git.mchus.pro/mchus/logpile/internal/privacy"
)
// BMCParser parses BMC diagnostic archives using vendor-specific parsers
@@ -66,6 +68,9 @@ func (p *BMCParser) parseFiles() error {
result.Filename = p.result.Filename
appendExtractionWarnings(result, p.files)
if scan := runPrivacyScan(p.files); scan != nil {
result.PrivacyScan = scan
}
if result.CollectedAt.IsZero() {
if ts := inferCollectedAtFromExtractedFiles(p.files); !ts.IsZero() {
result.CollectedAt = ts.UTC()
@@ -76,6 +81,28 @@ func (p *BMCParser) parseFiles() error {
return nil
}
// PrivacyScanEnabled reports whether the customer-data scan runs. It is on by
// default and disabled by LOGPILE_PRIVACY_SCAN=0 / false.
func PrivacyScanEnabled() bool {
switch strings.ToLower(strings.TrimSpace(os.Getenv("LOGPILE_PRIVACY_SCAN"))) {
case "0", "false", "off", "no":
return false
default:
return true
}
}
func runPrivacyScan(files []ExtractedFile) *models.PrivacyScan {
if !PrivacyScanEnabled() {
return nil
}
in := make([]privacy.File, 0, len(files))
for _, f := range files {
in = append(in, privacy.File{Path: f.Path, Content: f.Content})
}
return privacy.Scan(in)
}
func inferCollectedAtFromExtractedFiles(files []ExtractedFile) time.Time {
var latestReliable time.Time
var latestAny time.Time