security: harden inputs, fix shell injection, optimize DB access

- Fix command injection in hook script (pass paths via sys.argv)
- Add sanitize_name/sanitize_content validators in config.py
- Add 10MB file size guard + symlink skip in miners
- Fix SQLite connection leak in knowledge_graph.py (reuse connection)
- Use `with conn:` for proper transaction handling
- Consolidate shared palace operations into palace.py
- Add write-ahead log for audit trail on writes/deletes
- Add metadata cache with 30s TTL for status/taxonomy calls
- Upgrade md5 → sha256 for drawer/triple IDs
- Harden file permissions (0o700/0o600)
- Pin chromadb>=0.5.0,<0.7

Based on PR #252 by @anthonyonazure with lint fixes applied.

Co-Authored-By: anthonyonazure <anthonyonazure@users.noreply.github.com>
This commit is contained in:
bensig
2026-04-09 08:06:30 -07:00
parent 963c04cf45
commit 1d19dfc9d5
8 changed files with 389 additions and 203 deletions
+56
View File
@@ -6,8 +6,54 @@ Priority: env vars > config file (~/.mempalace/config.json) > defaults
import json
import os
import re
from pathlib import Path
# ── Input validation ──────────────────────────────────────────────────────────
# Shared sanitizers for wing/room/entity names. Prevents path traversal,
# excessively long strings, and special characters that could cause issues
# in file paths, SQLite, or ChromaDB metadata.
MAX_NAME_LENGTH = 128
_SAFE_NAME_RE = re.compile(r"^[a-zA-Z0-9][a-zA-Z0-9_ .'-]{0,126}[a-zA-Z0-9]?$")
def sanitize_name(value: str, field_name: str = "name") -> str:
"""Validate and sanitize a wing/room/entity name.
Raises ValueError if the name is invalid.
"""
if not isinstance(value, str) or not value.strip():
raise ValueError(f"{field_name} must be a non-empty string")
value = value.strip()
if len(value) > MAX_NAME_LENGTH:
raise ValueError(f"{field_name} exceeds maximum length of {MAX_NAME_LENGTH} characters")
# Block path traversal
if ".." in value or "/" in value or "\\" in value:
raise ValueError(f"{field_name} contains invalid path characters")
# Block null bytes
if "\x00" in value:
raise ValueError(f"{field_name} contains null bytes")
return value
def sanitize_content(value: str, max_length: int = 100_000) -> str:
"""Validate drawer/diary content length."""
if not isinstance(value, str) or not value.strip():
raise ValueError("content must be a non-empty string")
if len(value) > max_length:
raise ValueError(f"content exceeds maximum length of {max_length} characters")
if "\x00" in value:
raise ValueError("content contains null bytes")
return value
DEFAULT_PALACE_PATH = os.path.expanduser("~/.mempalace/palace")
DEFAULT_COLLECTION_NAME = "mempalace_drawers"
@@ -126,6 +172,11 @@ class MempalaceConfig:
def init(self):
"""Create config directory and write default config.json if it doesn't exist."""
self._config_dir.mkdir(parents=True, exist_ok=True)
# Restrict directory permissions to owner only (Unix)
try:
self._config_dir.chmod(0o700)
except (OSError, NotImplementedError):
pass # Windows doesn't support Unix permissions
if not self._config_file.exists():
default_config = {
"palace_path": DEFAULT_PALACE_PATH,
@@ -135,6 +186,11 @@ class MempalaceConfig:
}
with open(self._config_file, "w") as f:
json.dump(default_config, f, indent=2)
# Restrict config file to owner read/write only
try:
self._config_file.chmod(0o600)
except (OSError, NotImplementedError):
pass
return self._config_file
def save_people_map(self, people_map):