Harden PDF document markers against cross-owner upload access (#445)

Route PDF lookups through UploadHandler.resolve_upload, reject poisoned pdf_source markers on document create/update, and add regression tests.

Co-authored-by: Cursor <cursoragent@cursor.com>

src/pdf_form_doc.py

@@ -167,9 +167,18 @@ def find_source_upload_id(content: str) -> Optional[str]:
 
     Matches both the form-source marker (`pdf_form_source`) used for fillable
     PDFs and the plain marker (`pdf_source`) used for any imported PDF.
+    Rejects malformed ids (path traversal, wrong shape) before any lookup.
     """
+    from src.upload_handler import is_valid_upload_id
+
     m = _FRONT_MATTER_RE.search(content or "") or _PLAIN_FRONT_MATTER_RE.search(content or "")
-    return m.group("upload_id") if m else None
+    if not m:
+        return None
+    upload_id = m.group("upload_id")
+    if not is_valid_upload_id(upload_id):
+        logger.warning("Ignoring invalid pdf_source upload_id in document content: %r", upload_id)
+        return None
+    return upload_id
 
 
 def render_plain_pdf_markdown(upload_id: str, title: str, body_text: Optional[str] = None) -> str:

src/upload_handler.py

@@ -29,6 +29,14 @@ import logging
 
 logger = logging.getLogger(__name__)
 
+UPLOAD_ID_RE = re.compile(r"^[0-9a-fA-F]{32}\.[A-Za-z0-9]+$")
+
+
+def is_valid_upload_id(upload_id: str) -> bool:
+    """Return True when *upload_id* matches the canonical uploads.json id format."""
+    return UPLOAD_ID_RE.fullmatch(upload_id or "") is not None
+
+
 class UploadHandler:
     def __init__(self, base_dir: str, upload_dir: str):
         self.base_dir = base_dir
@@ -223,8 +231,7 @@ class UploadHandler:
     
     def validate_upload_id(self, upload_id: str) -> bool:
         """Validate that the upload ID matches the expected pattern."""
-        pattern = r'^[0-9a-fA-F]{32}\.[A-Za-z0-9]+$'
-        return re.fullmatch(pattern, upload_id) is not None
+        return is_valid_upload_id(upload_id)
 
     def _inside_upload_dir(self, path: str) -> bool:
         """Check if path is inside the upload directory."""