Standard production layout: the OKR app (was nested under AINative_OKR_CASAN5/) is now
the repository root. No more wrapper directory.
- Promote AINative_OKR_CASAN5/* -> repo root (backend/ frontend/ packages/ apps/
.specify/ docs/ infra/ nginx/ scripts/ + configs). Merge tool dirs: .gitea (kept the
active deploy ci.yml, added harness-ci.yml + runbooks), .claude (agents/commands +
launch.json), .github moved up.
- Remove redundant: 00_SUBMISSION_PACKAGE, scattered root notes (FPT_CASAN_Full.md,
tu-tuong-casan.md, casan-tu-sinh..., casan_harness_assessment.md, source-review...,
README_CASAN5_REFINED.md), casan-next-plans/ and optimize-docs/ (competition/planning
artifacts — roadmap + design history preserved in git log / commit messages).
- Update all references to the old layout:
- .gitea/workflows/{ci,harness-ci}.yml, .github/workflows/{ci,deploy}.yml:
working-directory .; drop AINative_OKR_CASAN5/ prefix; .specify/{tests,scripts}
-> packages/casan-harness/... (.specify/logs state kept)
- .claude/launch.json, .gitea/*-runbook.md: path prefixes
- CLAUDE.md, README.md: docs/input -> apps/okr/domain/input
- policy-bundle.yaml: 8 policy paths -> packages/casan-harness/...; manifest re-signed
- secrets-scan.sh: fixture excludes -> new package/domain paths.
Full gate from the new root: PASS=64 FAIL=0 SKIP=3.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
86 lines
3.0 KiB
Python
Executable File
86 lines
3.0 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
"""CASAN H4 PII masker driven by packages/casan-harness/security/pii-rules.yaml.
|
|
|
|
Reads content on stdin, applies every `action: mask` rule from the rules
|
|
file, and writes the masked content to stdout. Type-specific replacement
|
|
tokens are preserved so downstream evidence stays stable
|
|
(***MASKED_EMAIL***, ***MASKED_PHONE***, ***MASKED_ID***).
|
|
|
|
This makes pii-rules.yaml the source of truth for PII masking instead of
|
|
dead config: editing/removing a rule changes runtime behavior.
|
|
"""
|
|
import re
|
|
import sys
|
|
|
|
REPLACEMENT_BY_TYPE = {
|
|
"email": "***MASKED_EMAIL***",
|
|
"phone": "***MASKED_PHONE***",
|
|
"personal_id": "***MASKED_ID***",
|
|
"address": "***MASKED_ADDRESS***",
|
|
}
|
|
|
|
|
|
def load_rules(path):
|
|
rules, cur = [], {}
|
|
with open(path, encoding="utf-8") as fh:
|
|
for raw in fh:
|
|
s = raw.strip()
|
|
m = re.match(r"-\s*id:\s*(\S+)", s)
|
|
if m:
|
|
if cur:
|
|
rules.append(cur)
|
|
cur = {"id": m.group(1)}
|
|
continue
|
|
m = re.match(r'type:\s*"?([^"\s]+)"?', s)
|
|
if m:
|
|
cur["type"] = m.group(1)
|
|
continue
|
|
m = re.match(r'regex:\s*"(.*)"\s*$', s)
|
|
if m:
|
|
# YAML double-quoted: collapse \\ -> \ to recover the real regex.
|
|
cur["regex"] = m.group(1).replace("\\\\", "\\")
|
|
continue
|
|
m = re.match(r"action:\s*(\S+)", s)
|
|
if m:
|
|
cur["action"] = m.group(1)
|
|
continue
|
|
if cur:
|
|
rules.append(cur)
|
|
return rules
|
|
|
|
|
|
def main():
|
|
data = sys.stdin.read()
|
|
# SEC-08 (M-06): FAIL CLOSED. Previously a missing rules file, an unreadable
|
|
# file, or a broken rule regex all emitted the RAW data — so a mask rule that
|
|
# failed to load silently leaked the PII it was meant to hide. Now any such
|
|
# condition emits NOTHING and exits non-zero: no unmasked content ever escapes.
|
|
if len(sys.argv) < 2:
|
|
sys.stderr.write("PII_MASK_FAIL no rules file provided (fail-closed)\n")
|
|
return 1
|
|
try:
|
|
rules = load_rules(sys.argv[1])
|
|
except OSError as exc:
|
|
sys.stderr.write(f"PII_MASK_FAIL rules file unreadable (fail-closed): {exc}\n")
|
|
return 1
|
|
# Pre-compile every mask rule; a broken regex is fatal (that PII type would
|
|
# otherwise pass through unmasked). Validate all BEFORE emitting anything.
|
|
compiled = []
|
|
for rule in rules:
|
|
if rule.get("action") != "mask" or "regex" not in rule:
|
|
continue
|
|
token = REPLACEMENT_BY_TYPE.get(rule.get("type", ""), "***MASKED***")
|
|
try:
|
|
compiled.append((re.compile(rule["regex"]), token))
|
|
except re.error as exc:
|
|
sys.stderr.write(f"PII_MASK_FAIL bad regex in rule {rule.get('id')} (fail-closed): {exc}\n")
|
|
return 1
|
|
for rx, token in compiled:
|
|
data = rx.sub(token, data)
|
|
sys.stdout.write(data)
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
raise SystemExit(main())
|