| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| 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:
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:
Bluetooth: L2CAP: Validate L2CAP_INFO_RSP payload length before access
l2cap_information_rsp() checks that cmd_len covers the fixed
l2cap_info_rsp header (type + result, 4 bytes) but then reads
rsp->data without verifying that the payload is present:
- L2CAP_IT_FEAT_MASK calls get_unaligned_le32(rsp->data), which reads
4 bytes past the header (needs cmd_len >= 8).
- L2CAP_IT_FIXED_CHAN reads rsp->data[0], 1 byte past the header
(needs cmd_len >= 5).
A truncated L2CAP_INFO_RSP with result == L2CAP_IR_SUCCESS triggers an
out-of-bounds read of adjacent skb data.
Guard each data access with the required payload length check. If the
payload is too short, skip the read and let the state machine complete
with safe defaults (feat_mask and remote_fixed_chan remain zero from
kzalloc), so the info timer cleanup and l2cap_conn_start() still run
and the connection is not stalled. |
| In the Linux kernel, the following vulnerability has been resolved:
smb: client: fix krb5 mount with username option
Customer reported that some of their krb5 mounts were failing against
a single server as the client was trying to mount the shares with
wrong credentials. It turned out the client was reusing SMB session
from first mount to try mounting the other shares, even though a
different username= option had been specified to the other mounts.
By using username mount option along with sec=krb5 to search for
principals from keytab is supported by cifs.upcall(8) since
cifs-utils-4.8. So fix this by matching username mount option in
match_session() even with Kerberos.
For example, the second mount below should fail with -ENOKEY as there
is no 'foobar' principal in keytab (/etc/krb5.keytab). The client
ends up reusing SMB session from first mount to perform the second
one, which is wrong.
```
$ ktutil
ktutil: add_entry -password -p testuser -k 1 -e aes256-cts
Password for testuser@ZELDA.TEST:
ktutil: write_kt /etc/krb5.keytab
ktutil: quit
$ klist -ke
Keytab name: FILE:/etc/krb5.keytab
KVNO Principal
---- ----------------------------------------------------------------
1 testuser@ZELDA.TEST (aes256-cts-hmac-sha1-96)
$ mount.cifs //w22-root2/scratch /mnt/1 -o sec=krb5,username=testuser
$ mount.cifs //w22-root2/scratch /mnt/2 -o sec=krb5,username=foobar
$ mount -t cifs | grep -Po 'username=\K\w+'
testuser
testuser
``` |
| In the Linux kernel, the following vulnerability has been resolved:
ip_tunnel: adapt iptunnel_xmit_stats() to NETDEV_PCPU_STAT_DSTATS
Blamed commits forgot that vxlan/geneve use udp_tunnel[6]_xmit_skb() which
call iptunnel_xmit_stats().
iptunnel_xmit_stats() was assuming tunnels were only using
NETDEV_PCPU_STAT_TSTATS.
@syncp offset in pcpu_sw_netstats and pcpu_dstats is different.
32bit kernels would either have corruptions or freezes if the syncp
sequence was overwritten.
This patch also moves pcpu_stat_type closer to dev->{t,d}stats to avoid
a potential cache line miss since iptunnel_xmit_stats() needs to read it. |
| In the Linux kernel, the following vulnerability has been resolved:
netfilter: ctnetlink: fix use-after-free in ctnetlink_dump_exp_ct()
ctnetlink_dump_exp_ct() stores a conntrack pointer in cb->data for the
netlink dump callback ctnetlink_exp_ct_dump_table(), but drops the
conntrack reference immediately after netlink_dump_start(). When the
dump spans multiple rounds, the second recvmsg() triggers the dump
callback which dereferences the now-freed conntrack via nfct_help(ct),
leading to a use-after-free on ct->ext.
The bug is that the netlink_dump_control has no .start or .done
callbacks to manage the conntrack reference across dump rounds. Other
dump functions in the same file (e.g. ctnetlink_get_conntrack) properly
use .start/.done callbacks for this purpose.
Fix this by adding .start and .done callbacks that hold and release the
conntrack reference for the duration of the dump, and move the
nfct_help() call after the cb->args[0] early-return check in the dump
callback to avoid dereferencing ct->ext unnecessarily.
BUG: KASAN: slab-use-after-free in ctnetlink_exp_ct_dump_table+0x4f/0x2e0
Read of size 8 at addr ffff88810597ebf0 by task ctnetlink_poc/133
CPU: 1 UID: 0 PID: 133 Comm: ctnetlink_poc Not tainted 7.0.0-rc2+ #3 PREEMPTLAZY
Call Trace:
<TASK>
ctnetlink_exp_ct_dump_table+0x4f/0x2e0
netlink_dump+0x333/0x880
netlink_recvmsg+0x3e2/0x4b0
? aa_sk_perm+0x184/0x450
sock_recvmsg+0xde/0xf0
Allocated by task 133:
kmem_cache_alloc_noprof+0x134/0x440
__nf_conntrack_alloc+0xa8/0x2b0
ctnetlink_create_conntrack+0xa1/0x900
ctnetlink_new_conntrack+0x3cf/0x7d0
nfnetlink_rcv_msg+0x48e/0x510
netlink_rcv_skb+0xc9/0x1f0
nfnetlink_rcv+0xdb/0x220
netlink_unicast+0x3ec/0x590
netlink_sendmsg+0x397/0x690
__sys_sendmsg+0xf4/0x180
Freed by task 0:
slab_free_after_rcu_debug+0xad/0x1e0
rcu_core+0x5c3/0x9c0 |
| In the Linux kernel, the following vulnerability has been resolved:
netfilter: nf_conntrack_sip: fix Content-Length u32 truncation in sip_help_tcp()
sip_help_tcp() parses the SIP Content-Length header with
simple_strtoul(), which returns unsigned long, but stores the result in
unsigned int clen. On 64-bit systems, values exceeding UINT_MAX are
silently truncated before computing the SIP message boundary.
For example, Content-Length 4294967328 (2^32 + 32) is truncated to 32,
causing the parser to miscalculate where the current message ends. The
loop then treats trailing data in the TCP segment as a second SIP
message and processes it through the SDP parser.
Fix this by changing clen to unsigned long to match the return type of
simple_strtoul(), and reject Content-Length values that exceed the
remaining TCP payload length. |
| In the Linux kernel, the following vulnerability has been resolved:
netfilter: nf_conntrack_h323: fix OOB read in decode_int() CONS case
In decode_int(), the CONS case calls get_bits(bs, 2) to read a length
value, then calls get_uint(bs, len) without checking that len bytes
remain in the buffer. The existing boundary check only validates the
2 bits for get_bits(), not the subsequent 1-4 bytes that get_uint()
reads. This allows a malformed H.323/RAS packet to cause a 1-4 byte
slab-out-of-bounds read.
Add a boundary check for len bytes after get_bits() and before
get_uint(). |
