add mask-secret tool and rule

2026-08-13 01:59:42 +00:00
parent 6290dadb62
commit 2809072812
2 changed files with 132 additions and 0 deletions
@@ -0,0 +1,107 @@
+#!/usr/bin/env python3
+"""Mask a secret everywhere the chat history keeps it.
+
+Read the secret on stdin, never as an argument — argv is visible in `ps` to any
+local user, and it lands in the transcript a second time.
+
+    printf '%s' "$SECRET" | tools/mask-secret.py
+
+Replaces the secret with asterisks of the SAME LENGTH. That matters: the live
+session is appending to its transcript while this runs, so the file is opened
+'r+b' and overwritten in place. No rename, no truncate, the inode survives and
+the writer never notices. A `sed -i` would swap the inode out and the running
+session's appends would vanish into an unlinked file.
+
+Covers both stores a human can actually read back:
+  - Claude Code transcripts   ~/.claude/projects/**/*.jsonl
+  - Postgres                  chat_session_events (what the web chat replays)
+
+One paste lands in a transcript about three times — the `user` message, a
+`queue-operation` record, and a rolling `last-prompt` cache — plus once more for
+every command that carries it. Do not assume one hit.
+"""
+
+import os
+import re
+import subprocess
+import sys
+from pathlib import Path
+
+PROJECTS = Path.home() / ".claude" / "projects"
+PGDB = os.environ.get("MASK_PGDB", "officer_dev")
+PGHOST = os.environ.get("MASK_PGHOST", "127.0.0.1")
+PGUSER = os.environ.get("MASK_PGUSER", "postgres")
+
+
+def mask_file(path: Path, secret: bytes, mask: bytes) -> int:
+    """Overwrite in place, preserving the inode. Returns occurrences masked."""
+    try:
+        with open(path, "r+b") as f:
+            data = f.read()
+            hits = [m.start() for m in re.finditer(re.escape(secret), data)]
+            for off in hits:
+                f.seek(off)
+                f.write(mask)
+            f.flush()
+            os.fsync(f.fileno())
+        return len(hits)
+    except (OSError, PermissionError) as err:
+        print(f"  ! {path}: {err}", file=sys.stderr)
+        return 0
+
+
+def mask_postgres(secret: str, mask: str) -> int:
+    """Replace inside the jsonb payload. Returns rows updated, -1 if unavailable."""
+    sql = (
+        "update chat_session_events set event = "
+        "replace(event::text, %(s)s, %(m)s)::jsonb "
+        "where event::text like %(l)s;"
+    )
+    # psql has no bind params, so quote by doubling any single quotes. The secret
+    # is hex/base64 in practice, but never build SQL from unchecked input blindly.
+    q = lambda v: "'" + v.replace("'", "''") + "'"
+    stmt = sql.replace("%(s)s", q(secret)).replace("%(m)s", q(mask)).replace("%(l)s", q(f"%{secret}%"))
+    env = {**os.environ, "PGPASSWORD": os.environ.get("MASK_PGPASSWORD", "postgres")}
+    try:
+        out = subprocess.run(
+            ["psql", "-h", PGHOST, "-U", PGUSER, "-d", PGDB, "-tAc", stmt],
+            capture_output=True, text=True, env=env, timeout=30,
+        )
+    except (FileNotFoundError, subprocess.TimeoutExpired):
+        return -1
+    if out.returncode != 0:
+        print(f"  ! postgres: {out.stderr.strip()[:120]}", file=sys.stderr)
+        return -1
+    return int(out.stdout.strip().split()[-1]) if out.stdout.strip() else 0
+
+
+def main() -> int:
+    secret = sys.stdin.read().strip()
+    if len(secret) < 12:
+        print("refusing: secret under 12 chars would mask too much", file=sys.stderr)
+        return 2
+    mask = "*" * len(secret)
+    sb, mb = secret.encode(), mask.encode()
+
+    total = 0
+    for path in sorted(PROJECTS.rglob("*.jsonl")):
+        n = mask_file(path, sb, mb)
+        if n:
+            total += n
+            print(f"  {n:>3}  {path}")
+    print(f"transcripts: {total} occurrence(s) masked")
+
+    rows = mask_postgres(secret, mask)
+    if rows < 0:
+        print("postgres: skipped (psql unavailable or errored)")
+    else:
+        print(f"postgres: {rows} row(s) updated")
+
+    print("\nStill holding the real value, deliberately:")
+    print("  - the tool's own config (that is how it authenticates)")
+    print("  - this session's live context, re-sent to the API each turn")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())