| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| Firebird is an open-source relational database management system. In versions prior to 5.0.4, 4.0.7 and 3.0.14, when deserializing a slice packet, the xdr_datum() function does not validate that a cstring length conforms to the slice descriptor bounds, allowing a cstring longer than the allocated buffer to overflow it. An unauthenticated attacker can exploit this by sending a crafted packet to the server, potentially causing a crash or other security impact. This issue has been fixed in versions 5.0.4, 4.0.7 and 3.0.14. |
| 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 trigger server-side requests to arbitrary internal targets through `POST /settings/jellyfin/server-url-verify`. The endpoint accepts a user-controlled URL, appends `/system/info/public`, and sends a server-side HTTP request with Guzzle. Because there is no restriction on internal hosts, loopback addresses, or private network ranges, this can be abused for SSRF and internal network probing. Any ordinary authenticated user can use this endpoint to make the server connect to arbitrary internal targets and distinguish between different network states. This enables SSRF-based internal reconnaissance, including host discovery, port-state probing, and service fingerprinting. In certain deployments, it may also be usable to reach internal administrative services or cloud metadata endpoints that are not directly accessible from the outside. Version 0.71.1 fixes the issue. |
| xrdp is an open source RDP server. In versions through 0.10.5, xrdp does not implement verification for the Message Authentication Code (MAC) signature of encrypted RDP packets when using the "Classic RDP Security" layer. While the sender correctly generates signatures, the receiving logic lacks the necessary implementation to validate the 8-byte integrity signature, causing it to be silently ignored. An unauthenticated attacker with man-in-the-middle (MITM) capabilities can exploit this missing check to modify encrypted traffic in transit without detection. It does not affect connections where the TLS security layer is enforced. This issue has been fixed in version 0.10.6. If users are unable to immediately upgrade, they should configure xrdp.ini to enforce TLS security (security_layer=tls) to ensure end-to-end integrity. |
| xrdp is an open source RDP server. In versions through 0.10.5, the session execution component did not properly handle an error during the privilege drop process. This improper privilege management could allow an authenticated local attacker to escalate privileges to root and execute arbitrary code on the system. An additional exploit would be needed to facilitate this. This issue has been fixed in version 0.10.6. |
| xrdp is an open source RDP server. Versions through 0.10.5 contain a heap-based buffer overflow vulnerability in the NeutrinoRDP module. When proxying RDP sessions from xrdp to another server, the module fails to properly validate the size of reassembled fragmented virtual channel data against its allocated memory buffer. A malicious downstream RDP server (or an attacker capable of performing a Man-in-the-Middle attack) could exploit this flaw to cause memory corruption, potentially leading to a Denial of Service (DoS) or Remote Code Execution (RCE). The NeutrinoRDP module is not built by default. This vulnerability only affects environments where the module has been explicitly compiled and enabled. Users can verify if the module is built by checking for --enable-neutrinordp in the output of the xrdp -v command. This issue has been fixed in version 0.10.6. |
| In the Linux kernel, the following vulnerability has been resolved:
staging: rtl8723bs: initialize le_tmp64 in rtw_BIP_verify()
Initialize le_tmp64 to zero in rtw_BIP_verify() to prevent using
uninitialized data.
Smatch warns that only 6 bytes are copied to this 8-byte (u64)
variable, leaving the last two bytes uninitialized:
drivers/staging/rtl8723bs/core/rtw_security.c:1308 rtw_BIP_verify()
warn: not copying enough bytes for '&le_tmp64' (8 vs 6 bytes)
Initializing the variable at the start of the function fixes this
warning and ensures predictable behavior. |
| In the Linux kernel, the following vulnerability has been resolved:
NFC: digital: Bounds check NFC-A cascade depth in SDD response handler
The NFC-A anti-collision cascade in digital_in_recv_sdd_res() appends 3
or 4 bytes to target->nfcid1 on each round, but the number of cascade
rounds is controlled entirely by the peer device. The peer sets the
cascade tag in the SDD_RES (deciding 3 vs 4 bytes) and the
cascade-incomplete bit in the SEL_RES (deciding whether another round
follows).
ISO 14443-3 limits NFC-A to three cascade levels and target->nfcid1 is
sized accordingly (NFC_NFCID1_MAXSIZE = 10), but nothing in the driver
actually enforces this. This means a malicious peer can keep the
cascade running, writing past the heap-allocated nfc_target with each
round.
Fix this by rejecting the response when the accumulated UID would exceed
the buffer.
Commit e329e71013c9 ("NFC: nci: Bounds check struct nfc_target arrays")
fixed similar missing checks against the same field on the NCI path. |
| xrdp is an open source RDP server. Versions through 0.10.5 have a heap-based buffer overflow in the EGFX (graphics dynamic virtual channel) implementation due to insufficient validation of client-controlled size parameters, allowing an out-of-bounds write via crafted PDUs. Pre-authentication exploitation can crash the process, while post-authentication exploitation may achieve remote code execution. This issue has been fixed in version 0.10.6. If users are unable to immediately update, they should run xrdp as a non-privileged user (default since 0.10.2) to limit the impact of successful exploitation. |
| 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. |
| 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:
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:
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> |
