Skip to content

"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/

Python

fix(calibre): harden Zip Slip check and replace rglob with calibredb

ChengYed6fb8cc52b8a
diff --git a/calibre/agent-harness/cli_anything/calibre/core/export.py b/calibre/agent-harness/cli_anything/calibre/core/export.py
index 9b52b7fae..e4b27659c 100644
--- a/calibre/agent-harness/cli_anything/calibre/core/export.py
+++ b/calibre/agent-harness/cli_anything/calibre/core/export.py
@@ -301,11 +301,14 @@ def export_chapters_pdf(
# Step 2: extract EPUB and parse chapter list
epub_dir = Path(tmpdir) / "epub_content"
epub_dir.mkdir()
+ resolved_epub_dir = epub_dir.resolve()
with zipfile.ZipFile(epub_files[0]) as zf:
- # Validate each member path to prevent Zip Slip directory traversal attacks
+ # Validate each member path to prevent Zip Slip directory traversal attacks.
+ # Use Path.is_relative_to (Py3.10+) instead of str.startswith to avoid
+ # sibling-prefix bypasses (e.g. /tmp/epub vs /tmp/epub_evil).
for member in zf.infolist():
- member_path = (epub_dir / member.filename).resolve()
- if not str(member_path).startswith(str(epub_dir.resolve())):
+ member_path = (resolved_epub_dir / member.filename).resolve()
+ if not member_path.is_relative_to(resolved_epub_dir):
raise ValueError(f"Unsafe EPUB entry rejected: {member.filename}")
zf.extract(member, epub_dir)
diff --git a/calibre/agent-harness/cli_anything/calibre/core/library.py b/calibre/agent-harness/cli_anything/calibre/core/library.py
index 3ef051047..363b19b95 100644
--- a/calibre/agent-harness/cli_anything/calibre/core/library.py
+++ b/calibre/agent-harness/cli_anything/calibre/core/library.py
@@ -1,9 +1,7 @@
"""Library operations — wraps calibredb list, search, add, remove, export."""
import json
-import os
from pathlib import Path
-from typing import Any
from cli_anything.calibre.utils.calibre_backend import (
run_calibredb,
@@ -27,16 +25,44 @@ def library_info(library_path: str) -> dict:
else:
book_count = 0
- # Count format types by scanning library directory for book files
+ # Derive format counts from calibredb metadata instead of recursively scanning
+ # the library directory, which is slow and I/O-heavy on large libraries.
format_counts: dict[str, int] = {}
- lib = Path(library_path)
- skip_exts = {".db", ".jpg", ".png", ".opf", ".sqlite", ""}
- for p in lib.rglob("*"):
- if p.is_file():
- ext = p.suffix.upper().lstrip(".")
- if ext and ext not in {"DB", "JPG", "PNG", "OPF", "SQLITE", "WEBP", "GIF"}:
- format_counts[ext] = format_counts.get(ext, 0) + 1
+ formats_result = run_calibredb(
+ ["list", "--fields=formats", "--for-machine"],
+ library_path=library_path,
+ )
+ formats_output = formats_result["stdout"].strip()
+ if formats_output:
+ try:
+ rows = json.loads(formats_output)
+ except json.JSONDecodeError:
+ rows = []
+
+ if isinstance(rows, dict):
+ rows = list(rows.values())
+ elif not isinstance(rows, list):
+ rows = []
+
+ for row in rows:
+ if not isinstance(row, dict):
+ continue
+ value = row.get("formats")
+ if not value:
+ continue
+ if isinstance(value, str):
+ fmts = [f.strip() for f in value.split(",") if f.strip()]
+ elif isinstance(value, list):
+ fmts = [str(f).strip() for f in value if str(f).strip()]
+ else:
+ continue
+ for fmt in fmts:
+ # calibredb returns paths like "/.../book.epub" or bare "EPUB"
+ ext = Path(fmt).suffix.lstrip(".").upper() or fmt.upper()
+ if ext and ext not in {"JPG", "PNG", "OPF", "SQLITE", "WEBP", "GIF", "DB"}:
+ format_counts[ext] = format_counts.get(ext, 0) + 1
+ lib = Path(library_path)
db_path = lib / "metadata.db"
db_size = db_path.stat().st_size if db_path.exists() else 0