| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| xrdp is an open source RDP server. Versions through 0.10.5 have an out-of-bounds read vulnerability in the pre-authentication RDP message parsing logic. A remote, unauthenticated attacker can trigger this flaw by sending a specially crafted sequence of packets during the initial connection phase. This vulnerability results from insufficient validation of input buffer lengths before processing dynamic channel communication. Successful exploitation can lead to a denial-of-service (DoS) condition via a process crash or potential disclosure of sensitive information from the service's memory space. This issue has been fixed in version 0.10.6. |
| xrdp is an open source RDP server. Versions through 0.10.5 allow an authenticated remote user to execute arbitrary commands on the server due to unsafe handling of the AlternateShell parameter in xrdp-sesman. When the AllowAlternateShell setting is enabled (which is the default when not explicitly configured), xrdp accepts a client-supplied AlternateShell value and executes it via /bin/sh -c during session initialization. This results in shell-interpreted execution of unsanitized, user-controlled input. This behavior effectively provides a scriptable remote command execution primitive over RDP within the security context of the authenticated user, occurring prior to normal window manager startup. This can bypass expected session initialization flows and operational assumptions that restrict execution to interactive desktop environments. This issue has been fixed in version 0.10.6. |
| NovumOS is a custom 32-bit operating system written in Zig and x86 Assembly. In versions prior to 0.24, Syscall 15 (MemoryMapRange) allows Ring 3 user-mode processes to map arbitrary virtual address ranges into their address space without validating against forbidden regions, including critical kernel structures such as the IDT, GDT, TSS, and page tables. A local attacker can exploit this to modify kernel interrupt handlers, resulting in privilege escalation from user mode to kernel context. This issue has been fixed in version 0.24. |
| Movary is a self hosted web app to track and rate a user's watched movies. Prior to version 0.71.1, an ordinary authenticated user can access the user-management endpoints `/settings/users` and use them to enumerate all users and create a new administrator account. This happens because the route definitions do not enforce admin-only middleware, and the controller-level authorization check uses a broken boolean condition. As a result, any user with a valid web session cookie can reach functionality that should be restricted to administrators. Version 0.71.1 patches the issue. |
| Movary is a self hosted web app to track and rate a user's watched movies. Prior to version 0.71.1, an ordinary authenticated user can escalate their own account to administrator by sending `isAdmin=true` to `PUT /settings/users/{userId}` for their own user ID. The endpoint is intended to let a user edit their own profile, but it updates the sensitive `isAdmin` field without any admin-only authorization check. Version 0.71.1 patches the issue. |
| NovumOS is a custom 32-bit operating system written in Zig and x86 Assembly. In versions prior to 0.24, Syscall 12 (JumpToUser) accepts an arbitrary entry point address from user-space registers without validation, allowing any Ring 3 user-mode process to jump to kernel addresses and execute arbitrary code in Ring 0 context, resulting in local privilege escalation. This issue has been fixed in version 0.24. If developers are unable to immediately update, they should restrict syscall access by running the system in single-user mode without Ring 3, and disable user-mode processes by only running kernel shell with no user processes. This issue has been fixed in version 0.24. |
| In the Linux kernel, the following vulnerability has been resolved:
smb: client: fix OOB reads parsing symlink error response
When a CREATE returns STATUS_STOPPED_ON_SYMLINK, smb2_check_message()
returns success without any length validation, leaving the symlink
parsers as the only defense against an untrusted server.
symlink_data() walks SMB 3.1.1 error contexts with the loop test "p <
end", but reads p->ErrorId at offset 4 and p->ErrorDataLength at offset
0. When the server-controlled ErrorDataLength advances p to within 1-7
bytes of end, the next iteration will read past it. When the matching
context is found, sym->SymLinkErrorTag is read at offset 4 from
p->ErrorContextData with no check that the symlink header itself fits.
smb2_parse_symlink_response() then bounds-checks the substitute name
using SMB2_SYMLINK_STRUCT_SIZE as the offset of PathBuffer from
iov_base. That value is computed as sizeof(smb2_err_rsp) +
sizeof(smb2_symlink_err_rsp), which is correct only when
ErrorContextCount == 0.
With at least one error context the symlink data sits 8 bytes deeper,
and each skipped non-matching context shifts it further by 8 +
ALIGN(ErrorDataLength, 8). The check is too short, allowing the
substitute name read to run past iov_len. The out-of-bound heap bytes
are UTF-16-decoded into the symlink target and returned to userspace via
readlink(2).
Fix this all up by making the loops test require the full context header
to fit, rejecting sym if its header runs past end, and bound the
substitute name against the actual position of sym->PathBuffer rather
than a fixed offset.
Because sub_offs and sub_len are 16bits, the pointer math will not
overflow here with the new greater-than. |
| In the Linux kernel, the following vulnerability has been resolved:
dmaengine: idxd: fix possible wrong descriptor completion in llist_abort_desc()
At the end of this function, d is the traversal cursor of flist, but the
code completes found instead. This can lead to issues such as NULL pointer
dereferences, double completion, or descriptor leaks.
Fix this by completing d instead of found in the final
list_for_each_entry_safe() loop. |
| In the Linux kernel, the following vulnerability has been resolved:
ksmbd: fix OOB write in QUERY_INFO for compound requests
When a compound request such as READ + QUERY_INFO(Security) is received,
and the first command (READ) consumes most of the response buffer,
ksmbd could write beyond the allocated buffer while building a security
descriptor.
The root cause was that smb2_get_info_sec() checked buffer space using
ppntsd_size from xattr, while build_sec_desc() often synthesized a
significantly larger descriptor from POSIX ACLs.
This patch introduces smb_acl_sec_desc_scratch_len() to accurately
compute the final descriptor size beforehand, performs proper buffer
checking with smb2_calc_max_out_buf_len(), and uses exact-sized
allocation + iov pinning. |
| In the Linux kernel, the following vulnerability has been resolved:
ACPI: EC: clean up handlers on probe failure in acpi_ec_setup()
When ec_install_handlers() returns -EPROBE_DEFER on reduced-hardware
platforms, it has already started the EC and installed the address
space handler with the struct acpi_ec pointer as handler context.
However, acpi_ec_setup() propagates the error without any cleanup.
The caller acpi_ec_add() then frees the struct acpi_ec for non-boot
instances, leaving a dangling handler context in ACPICA.
Any subsequent AML evaluation that accesses an EC OpRegion field
dispatches into acpi_ec_space_handler() with the freed pointer,
causing a use-after-free:
BUG: KASAN: slab-use-after-free in mutex_lock (kernel/locking/mutex.c:289)
Write of size 8 at addr ffff88800721de38 by task init/1
Call Trace:
<TASK>
mutex_lock (kernel/locking/mutex.c:289)
acpi_ec_space_handler (drivers/acpi/ec.c:1362)
acpi_ev_address_space_dispatch (drivers/acpi/acpica/evregion.c:293)
acpi_ex_access_region (drivers/acpi/acpica/exfldio.c:246)
acpi_ex_field_datum_io (drivers/acpi/acpica/exfldio.c:509)
acpi_ex_extract_from_field (drivers/acpi/acpica/exfldio.c:700)
acpi_ex_read_data_from_field (drivers/acpi/acpica/exfield.c:327)
acpi_ex_resolve_node_to_value (drivers/acpi/acpica/exresolv.c:392)
</TASK>
Allocated by task 1:
acpi_ec_alloc (drivers/acpi/ec.c:1424)
acpi_ec_add (drivers/acpi/ec.c:1692)
Freed by task 1:
kfree (mm/slub.c:6876)
acpi_ec_add (drivers/acpi/ec.c:1751)
The bug triggers on reduced-hardware EC platforms (ec->gpe < 0)
when the GPIO IRQ provider defers probing. Once the stale handler
exists, any unprivileged sysfs read that causes AML to touch an
EC OpRegion (battery, thermal, backlight) exercises the dangling
pointer.
Fix this by calling ec_remove_handlers() in the error path of
acpi_ec_setup() before clearing first_ec. ec_remove_handlers()
checks each EC_FLAGS_* bit before acting, so it is safe to call
regardless of how far ec_install_handlers() progressed:
-ENODEV (handler not installed): only calls acpi_ec_stop()
-EPROBE_DEFER (handler installed): removes handler, stops EC |
| In the Linux kernel, the following vulnerability has been resolved:
net/x25: Fix overflow when accumulating packets
Add a check to ensure that `x25_sock.fraglen` does not overflow.
The `fraglen` also needs to be resetted when purging `fragment_queue` in
`x25_clear_queues()`. |
| In the Linux kernel, the following vulnerability has been resolved:
bpf: Fix unsound scalar forking in maybe_fork_scalars() for BPF_OR
maybe_fork_scalars() is called for both BPF_AND and BPF_OR when the
source operand is a constant. When dst has signed range [-1, 0], it
forks the verifier state: the pushed path gets dst = 0, the current
path gets dst = -1.
For BPF_AND this is correct: 0 & K == 0.
For BPF_OR this is wrong: 0 | K == K, not 0.
The pushed path therefore tracks dst as 0 when the runtime value is K,
producing an exploitable verifier/runtime divergence that allows
out-of-bounds map access.
Fix this by passing env->insn_idx (instead of env->insn_idx + 1) to
push_stack(), so the pushed path re-executes the ALU instruction with
dst = 0 and naturally computes the correct result for any opcode. |
| In the Linux kernel, the following vulnerability has been resolved:
ksmbd: unset conn->binding on failed binding request
When a multichannel SMB2_SESSION_SETUP request with
SMB2_SESSION_REQ_FLAG_BINDING fails ksmbd sets conn->binding = true
but never clears it on the error path. This leaves the connection in
a binding state where all subsequent ksmbd_session_lookup_all() calls
fall back to the global sessions table. This fix it by clearing
conn->binding = false in the error path. |
| In the Linux kernel, the following vulnerability has been resolved:
Bluetooth: SCO: Fix use-after-free in sco_recv_frame() due to missing sock_hold
sco_recv_frame() reads conn->sk under sco_conn_lock() but immediately
releases the lock without holding a reference to the socket. A concurrent
close() can free the socket between the lock release and the subsequent
sk->sk_state access, resulting in a use-after-free.
Other functions in the same file (sco_sock_timeout(), sco_conn_del())
correctly use sco_sock_hold() to safely hold a reference under the lock.
Fix by using sco_sock_hold() to take a reference before releasing the
lock, and adding sock_put() on all exit paths. |
| In the Linux kernel, the following vulnerability has been resolved:
netfilter: conntrack: add missing netlink policy validations
Hyunwoo Kim reports out-of-bounds access in sctp and ctnetlink.
These attributes are used by the kernel without any validation.
Extend the netlink policies accordingly.
Quoting the reporter:
nlattr_to_sctp() assigns the user-supplied CTA_PROTOINFO_SCTP_STATE
value directly to ct->proto.sctp.state without checking that it is
within the valid range. [..]
and: ... with exp->dir = 100, the access at
ct->master->tuplehash[100] reads 5600 bytes past the start of a
320-byte nf_conn object, causing a slab-out-of-bounds read confirmed by
UBSAN. |
| In the Linux kernel, the following vulnerability has been resolved:
xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fini()
After cancel_delayed_work_sync() is called from
xfrm_nat_keepalive_net_fini(), xfrm_state_fini() flushes remaining
states via __xfrm_state_delete(), which calls
xfrm_nat_keepalive_state_updated() to re-schedule nat_keepalive_work.
The following is a simple race scenario:
cpu0 cpu1
cleanup_net() [Round 1]
ops_undo_list()
xfrm_net_exit()
xfrm_nat_keepalive_net_fini()
cancel_delayed_work_sync(nat_keepalive_work);
xfrm_state_fini()
xfrm_state_flush()
xfrm_state_delete(x)
__xfrm_state_delete(x)
xfrm_nat_keepalive_state_updated(x)
schedule_delayed_work(nat_keepalive_work);
rcu_barrier();
net_complete_free();
net_passive_dec(net);
llist_add(&net->defer_free_list, &defer_free_list);
cleanup_net() [Round 2]
rcu_barrier();
net_complete_free()
kmem_cache_free(net_cachep, net);
nat_keepalive_work()
// on freed net
To prevent this, cancel_delayed_work_sync() is replaced with
disable_delayed_work_sync(). |
| In the Linux kernel, the following vulnerability has been resolved:
media: dvb-net: fix OOB access in ULE extension header tables
The ule_mandatory_ext_handlers[] and ule_optional_ext_handlers[] tables
in handle_one_ule_extension() are declared with 255 elements (valid
indices 0-254), but the index htype is derived from network-controlled
data as (ule_sndu_type & 0x00FF), giving a range of 0-255. When
htype equals 255, an out-of-bounds read occurs on the function pointer
table, and the OOB value may be called as a function pointer.
Add a bounds check on htype against the array size before either table
is accessed. Out-of-range values now cause the SNDU to be discarded. |
| In the Linux kernel, the following vulnerability has been resolved:
NFSD: Defer sub-object cleanup in export put callbacks
svc_export_put() calls path_put() and auth_domain_put() immediately
when the last reference drops, before the RCU grace period. RCU
readers in e_show() and c_show() access both ex_path (via
seq_path/d_path) and ex_client->name (via seq_escape) without
holding a reference. If cache_clean removes the entry and drops the
last reference concurrently, the sub-objects are freed while still
in use, producing a NULL pointer dereference in d_path.
Commit 2530766492ec ("nfsd: fix UAF when access ex_uuid or
ex_stats") moved kfree of ex_uuid and ex_stats into the
call_rcu callback, but left path_put() and auth_domain_put() running
before the grace period because both may sleep and call_rcu
callbacks execute in softirq context.
Replace call_rcu/kfree_rcu with queue_rcu_work(), which defers the
callback until after the RCU grace period and executes it in process
context where sleeping is permitted. This allows path_put() and
auth_domain_put() to be moved into the deferred callback alongside
the other resource releases. Apply the same fix to expkey_put(),
which has the identical pattern with ek_path and ek_client.
A dedicated workqueue scopes the shutdown drain to only NFSD
export release work items; flushing the shared
system_unbound_wq would stall on unrelated work from other
subsystems. nfsd_export_shutdown() uses rcu_barrier() followed
by flush_workqueue() to ensure all deferred release callbacks
complete before the export caches are destroyed.
Reviwed-by: Jeff Layton <jlayton@kernel.org> |
| In the Linux kernel, the following vulnerability has been resolved:
NFSD: Hold net reference for the lifetime of /proc/fs/nfs/exports fd
The /proc/fs/nfs/exports proc entry is created at module init
and persists for the module's lifetime. exports_proc_open()
captures the caller's current network namespace and stores
its svc_export_cache in seq->private, but takes no reference
on the namespace. If the namespace is subsequently torn down
(e.g. container destruction after the opener does setns() to a
different namespace), nfsd_net_exit() calls nfsd_export_shutdown()
which frees the cache. Subsequent reads on the still-open fd
dereference the freed cache_detail, walking a freed hash table.
Hold a reference on the struct net for the lifetime of the open
file descriptor. This prevents nfsd_net_exit() from running --
and thus prevents nfsd_export_shutdown() from freeing the cache
-- while any exports fd is open. cache_detail already stores
its net pointer (cd->net, set by cache_create_net()), so
exports_release() can retrieve it without additional per-file
storage. |
| In the Linux kernel, the following vulnerability has been resolved:
nfsd: fix heap overflow in NFSv4.0 LOCK replay cache
The NFSv4.0 replay cache uses a fixed 112-byte inline buffer
(rp_ibuf[NFSD4_REPLAY_ISIZE]) to store encoded operation responses.
This size was calculated based on OPEN responses and does not account
for LOCK denied responses, which include the conflicting lock owner as
a variable-length field up to 1024 bytes (NFS4_OPAQUE_LIMIT).
When a LOCK operation is denied due to a conflict with an existing lock
that has a large owner, nfsd4_encode_operation() copies the full encoded
response into the undersized replay buffer via read_bytes_from_xdr_buf()
with no bounds check. This results in a slab-out-of-bounds write of up
to 944 bytes past the end of the buffer, corrupting adjacent heap memory.
This can be triggered remotely by an unauthenticated attacker with two
cooperating NFSv4.0 clients: one sets a lock with a large owner string,
then the other requests a conflicting lock to provoke the denial.
We could fix this by increasing NFSD4_REPLAY_ISIZE to allow for a full
opaque, but that would increase the size of every stateowner, when most
lockowners are not that large.
Instead, fix this by checking the encoded response length against
NFSD4_REPLAY_ISIZE before copying into the replay buffer. If the
response is too large, set rp_buflen to 0 to skip caching the replay
payload. The status is still cached, and the client already received the
correct response on the original request. |
