🚨 CVE-2026-31412
In the Linux kernel, the following vulnerability has been resolved:

usb: gadget: f_mass_storage: Fix potential integer overflow in check_command_size_in_blocks()

The `check_command_size_in_blocks()` function calculates the data size
in bytes by left shifting `common->data_size_from_cmnd` by the block
size (`common->curlun->blkbits`). However, it does not validate whether
this shift operation will cause an integer overflow.

Initially, the block size is set up in `fsg_lun_open()` , and the
`common->data_size_from_cmnd` is set up in `do_scsi_command()`. During
initialization, there is no integer overflow check for the interaction
between two variables.

So if a malicious USB host sends a SCSI READ or WRITE command
requesting a large amount of data (`common->data_size_from_cmnd`), the
left shift operation can wrap around. This results in a truncated data
size, which can bypass boundary checks and potentially lead to memory
corruption or out-of-bounds accesses.

Fix this by using the check_shl_overflow() macro to safely perform the
shift and catch any overflows.

🎖@cveNotify

🚨 CVE-2026-31413
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.

🎖@cveNotify

🚨 CVE-2026-31414
In the Linux kernel, the following vulnerability has been resolved:

netfilter: nf_conntrack_expect: use expect->helper

Use expect->helper in ctnetlink and /proc to dump the helper name.
Using nfct_help() without holding a reference to the master conntrack
is unsafe.

Use exp->master->helper in ctnetlink path if userspace does not provide
an explicit helper when creating an expectation to retain the existing
behaviour. The ctnetlink expectation path holds the reference on the
master conntrack and nf_conntrack_expect lock and the nfnetlink glue
path refers to the master ct that is attached to the skb.

🎖@cveNotify

🚨 CVE-2023-5636
Unrestricted Upload of File with Dangerous Type vulnerability in ArslanSoft Education Portal allows Command Injection.

This issue affects Education Portal: before v1.1.

🎖@cveNotify

🚨 CVE-2023-5637
Unrestricted Upload of File with Dangerous Type vulnerability in ArslanSoft Education Portal allows Read Sensitive Strings Within an Executable.

This issue affects Education Portal: before v1.1.

🎖@cveNotify

🚨 CVE-2023-5806
Improper Neutralization of Special Elements used in an SQL Command ('SQL Injection') vulnerability in Mergen Software Quality Management System allows SQL Injection.

This issue affects Quality Management System: before v1.2.

🎖@cveNotify

🚨 CVE-2026-31406
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().

🎖@cveNotify

🚨 CVE-2026-31407
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.

🎖@cveNotify

🚨 CVE-2026-31408
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.

🎖@cveNotify

🚨 CVE-2026-31409
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.

🎖@cveNotify

🚨 CVE-2026-31410
In the Linux kernel, the following vulnerability has been resolved:

ksmbd: use volume UUID in FS_OBJECT_ID_INFORMATION

Use sb->s_uuid for a proper volume identifier as the primary choice.
For filesystems that do not provide a UUID, fall back to stfs.f_fsid
obtained from vfs_statfs().

🎖@cveNotify

🚨 CVE-2026-44916
In OpenStack Ironic before 35.0.2 (in a certain non-default configuration), instance_info['ks_template'] is rendered without sandboxing.

🎖@cveNotify

🚨 CVE-2025-57798
Joplin is an open source note-taking and to-do application that organises notes and lists into notebooks. Versions 3.6.14 and prior contain a Denial of Service (DoS) vulnerability in the title input functionality due to a lack of proper length validation. This flaw allows an attacker to cause an Out Of Memory (OOM) error and subsequent program termination by inserting an excessively long string into a note's title. This can be triggered either through direct user interface (UI) input or programmatically via the local web service API after compromising an authentication token. There are 2 primary methods of exploitation: via User Interface (UI) Input, and the Local Web Service API. A local user can directly type or paste an extremely long string into the title field when creating or editing a note Joplin runs a local web service (typically on port 41184) that allows programmatic interaction, such as creating or editing notes via HTTP API calls. If an attacker manages to exfiltrate or compromise the user's authentication token (e.g., through malware on the local system, or other local vulnerabilities), they can then send a crafted HTTP POST request to this local API. By including an excessively long string in the title parameter of this request, the application will attempt to allocate an unbounded amount of memory. This issue has been patched in version 3.7.1.

🎖@cveNotify

🚨 CVE-2026-34241
CtrlPanel is open-source billing software for hosting providers. Versions 1.1.1 and prior contain a Stored Cross-Site Scripting (XSS) vulnerability in the ticket reply notification system. Unsanitized reply content ($newmessage) is stored directly in database notification payloads and later rendered unescaped via Blade's {!! !!} syntax in the recipient's browser. The flaw exists in both App\Notifications\Ticket\Admin\AdminReplyNotification (triggered when a user replies, targeting admins) and App\Notifications\Ticket\User\ReplyNotification (triggered when an admin replies, targeting users), allowing arbitrary JavaScript execution in the victim's session context. A low-privileged attacker can exploit this to hijack admin sessions, harvest credentials via fake login prompts or keyloggers, and escalate privileges by performing administrative actions on the victim's behalf. The reverse path also enables a malicious or compromised admin to target regular users in the same manner. This issue has been fixed in version 1.2.0.

🎖@cveNotify

🚨 CVE-2026-45585
Microsoft is aware of a security feature bypass vulnerability in Windows publicly referred to as "YellowKey". The proof of concept for this vulnerability has been made public violating coordinated vulnerability best practices.
We are issuing this CVE to provide mitigation guidance that can be implemented to protect against this vulnerability until the security update is made available.

🎖@cveNotify

🚨 CVE-2026-31423
In the Linux kernel, the following vulnerability has been resolved:

net/sched: sch_hfsc: fix divide-by-zero in rtsc_min()

m2sm() converts a u32 slope to a u64 scaled value. For large inputs
(e.g. m1=4000000000), the result can reach 2^32. rtsc_min() stores
the difference of two such u64 values in a u32 variable `dsm` and
uses it as a divisor. When the difference is exactly 2^32 the
truncation yields zero, causing a divide-by-zero oops in the
concave-curve intersection path:

Oops: divide error: 0000
RIP: 0010:rtsc_min (net/sched/sch_hfsc.c:601)
Call Trace:
init_ed (net/sched/sch_hfsc.c:629)
hfsc_enqueue (net/sched/sch_hfsc.c:1569)
[...]

Widen `dsm` to u64 and replace do_div() with div64_u64() so the full
difference is preserved.

🎖@cveNotify

🚨 CVE-2008-4250
The Server service in Microsoft Windows 2000 SP4, XP SP2 and SP3, Server 2003 SP1 and SP2, Vista Gold and SP1, Server 2008, and 7 Pre-Beta allows remote attackers to execute arbitrary code via a crafted RPC request that triggers the overflow during path canonicalization, as exploited in the wild by Gimmiv.A in October 2008, aka "Server Service Vulnerability."

🎖@cveNotify

🚨 CVE-2009-1537
Unspecified vulnerability in the QuickTime Movie Parser Filter in quartz.dll in DirectShow in Microsoft DirectX 7.0 through 9.0c on Windows 2000 SP4, Windows XP SP2 and SP3, and Windows Server 2003 SP2 allows remote attackers to execute arbitrary code via a crafted QuickTime media file, as exploited in the wild in May 2009, aka "DirectX NULL Byte Overwrite Vulnerability."

🎖@cveNotify

🚨 CVE-2009-3459
Heap-based buffer overflow in Adobe Reader and Acrobat 7.x before 7.1.4, 8.x before 8.1.7, and 9.x before 9.2 allows remote attackers to execute arbitrary code via a crafted PDF file that triggers memory corruption, as exploited in the wild in October 2009. NOTE: some of these details are obtained from third party information.

🎖@cveNotify

🚨 CVE-2010-0249
Use-after-free vulnerability in Microsoft Internet Explorer 6, 6 SP1, 7, and 8 on Windows 2000 SP4; Windows XP SP2 and SP3; Windows Server 2003 SP2; Windows Vista Gold, SP1, and SP2; Windows Server 2008 Gold, SP2, and R2; and Windows 7 allows remote attackers to execute arbitrary code by accessing a pointer associated with a deleted object, related to incorrectly initialized memory and improper handling of objects in memory, as exploited in the wild in December 2009 and January 2010 during Operation Aurora, aka "HTML Object Memory Corruption Vulnerability."

🎖@cveNotify

🚨 CVE-2010-0806
Use-after-free vulnerability in the Peer Objects component (aka iepeers.dll) in Microsoft Internet Explorer 6, 6 SP1, and 7 allows remote attackers to execute arbitrary code via vectors involving access to an invalid pointer after the deletion of an object, as exploited in the wild in March 2010, aka "Uninitialized Memory Corruption Vulnerability."

🎖@cveNotify