mirror of
https://github.com/pewdiepie-archdaemon/odysseus.git
synced 2026-10-03 21:42:21 +02:00
Merge commit from fork
* fix(security): keep agent file tools out of the app state directory
The agent's read tools (read_file, grep, glob, ls) resolved model-supplied
paths against a root list whose first entry was the whole data directory.
That directory holds the session store, the auth database, the app
encryption key and the settings file, so prompt-injected content could ask
for any of them. No approval prompt stood in the way: reads are classified
read_workspace and pass the untrusted-context gate untouched, which is
correct for reading a workspace and wrong for reading the app's own state.
The agent gets data/agent_workspace/ instead, and the subprocess cwd and
HOME move with it so bash and read_file agree on where scratch files live.
The deny itself is a property of the path, not of the root it arrived
through, because three routes reach the same bytes and closing only the
first leaves the other two working:
- the default root list
- a workspace bound at or above the data directory, which vet_workspace
accepted and chat_routes auto-binds from a path named in the message
- a tool_path_extra_roots setting covering the data directory
_resolve_search_root also returned the workspace root unchecked when the
path was empty, so a bare ls enumerated the directory whatever the deny
list said. It now resolves that case through the same guards.
A containment rule rather than a filename deny list, so state files added
later are covered without anyone remembering to list them, and so a user's
own settings.json or app.db inside a real workspace is not caught.
Four directories of user content stay readable, because the application
hands their paths to the model and tells it to open them: the chat upload
manifest, downloaded mail attachments, personal docs (which covers the
runbook) and personal uploads.
* fix: enforce state deny during recursive file search
* fix: bound protected filesystem searches
* fix(security): reject inode aliases and workspace redirects
* fix(security): harden partitioned agent searches
* fix(security): report fallback worker exits promptly
* fix(security): clean up search readers and retain relative data roots
---------
Co-authored-by: RaresKeY <158580472+RaresKeY@users.noreply.github.com>
This commit is contained in:
@@ -54,6 +54,11 @@ GALLERY_DIR = os.path.join(DATA_DIR, "gallery")
|
||||
GALLERY_UPLOADS_DIR = os.path.join(DATA_DIR, "gallery_uploads")
|
||||
MEMORY_VECTORS_DIR = os.path.join(DATA_DIR, "memory_vectors")
|
||||
|
||||
# The only part of DATA_DIR the agent's file tools and subprocesses may touch.
|
||||
# Everything else under DATA_DIR is application state (session store, auth
|
||||
# database, encryption key, settings), and the agent has no business reading it.
|
||||
AGENT_WORKSPACE_DIR = os.path.join(DATA_DIR, "agent_workspace")
|
||||
|
||||
# Paths with an intentional dedicated env override, defaulting under DATA_DIR.
|
||||
MAIL_ATTACHMENTS_DIR = os.getenv("ODYSSEUS_MAIL_ATTACHMENTS_DIR", os.path.join(DATA_DIR, "mail-attachments"))
|
||||
# `or` (not os.getenv's default arg) so a PRESENT-but-EMPTY value falls back to
|
||||
|
||||
Reference in New Issue
Block a user