🚨 CVE-2026-8960
Spoofing issue in WebExtensions. This vulnerability was fixed in Firefox 151 and Thunderbird 151.

🎖@cveNotify

🚨 CVE-2026-30117
scalar/astro v0.1.13 was discovered to contain an arbitrary file upload vulnerability in the the scalar_url query parameter of the Scalar Proxy endpoint. This vulnerability allows attackers to execute arbitrary code via uploading a crafted SVG file.

🎖@cveNotify

🚨 CVE-2026-31395
In the Linux kernel, the following vulnerability has been resolved:

bnxt_en: fix OOB access in DBG_BUF_PRODUCER async event handler

The ASYNC_EVENT_CMPL_EVENT_ID_DBG_BUF_PRODUCER handler in
bnxt_async_event_process() uses a firmware-supplied 'type' field
directly as an index into bp->bs_trace[] without bounds validation.

The 'type' field is a 16-bit value extracted from DMA-mapped completion
ring memory that the NIC writes directly to host RAM. A malicious or
compromised NIC can supply any value from 0 to 65535, causing an
out-of-bounds access into kernel heap memory.

The bnxt_bs_trace_check_wrap() call then dereferences bs_trace->magic_byte
and writes to bs_trace->last_offset and bs_trace->wrapped, leading to
kernel memory corruption or a crash.

Fix by adding a bounds check and defining BNXT_TRACE_MAX as
DBG_LOG_BUFFER_FLUSH_REQ_TYPE_ERR_QPC_TRACE + 1 to cover all currently
defined firmware trace types (0x0 through 0xc).

🎖@cveNotify

🚨 CVE-2026-8948
Same-origin policy bypass in the DOM: Networking component. This vulnerability was fixed in Firefox 151 and Thunderbird 151.

🎖@cveNotify

🚨 CVE-2026-8949
Integer overflow in the Widget: Win32 component. This vulnerability was fixed in Firefox 151, Firefox ESR 140.11, Thunderbird 151, and Thunderbird 140.11.

🎖@cveNotify

🚨 CVE-2026-8950
Same-origin policy bypass in the Networking: HTTP component. This vulnerability was fixed in Firefox 151, Firefox ESR 140.11, Thunderbird 151, and Thunderbird 140.11.

🎖@cveNotify

🚨 CVE-2026-8951
Spoofing issue in the Toolbar component in Firefox for Android. This vulnerability was fixed in Firefox 151.

🎖@cveNotify

🚨 CVE-2026-8952
Privilege escalation in the Application Update component. This vulnerability was fixed in Firefox 151 and Thunderbird 151.

🎖@cveNotify

🚨 CVE-2026-23461
In the Linux kernel, the following vulnerability has been resolved:

Bluetooth: L2CAP: Fix use-after-free in l2cap_unregister_user

After commit ab4eedb790ca ("Bluetooth: L2CAP: Fix corrupted list in
hci_chan_del"), l2cap_conn_del() uses conn->lock to protect access to
conn->users. However, l2cap_register_user() and l2cap_unregister_user()
don't use conn->lock, creating a race condition where these functions can
access conn->users and conn->hchan concurrently with l2cap_conn_del().

This can lead to use-after-free and list corruption bugs, as reported
by syzbot.

Fix this by changing l2cap_register_user() and l2cap_unregister_user()
to use conn->lock instead of hci_dev_lock(), ensuring consistent locking
for the l2cap_conn structure.

🎖@cveNotify

🚨 CVE-2026-31411
In the Linux kernel, the following vulnerability has been resolved:

net: atm: fix crash due to unvalidated vcc pointer in sigd_send()

Reproducer available at [1].

The ATM send path (sendmsg -> vcc_sendmsg -> sigd_send) reads the vcc
pointer from msg->vcc and uses it directly without any validation. This
pointer comes from userspace via sendmsg() and can be arbitrarily forged:

int fd = socket(AF_ATMSVC, SOCK_DGRAM, 0);
ioctl(fd, ATMSIGD_CTRL); // become ATM signaling daemon
struct msghdr msg = { .msg_iov = &iov, ... };
*(unsigned long *)(buf + 4) = 0xdeadbeef; // fake vcc pointer
sendmsg(fd, &msg, 0); // kernel dereferences 0xdeadbeef

In normal operation, the kernel sends the vcc pointer to the signaling
daemon via sigd_enq() when processing operations like connect(), bind(),
or listen(). The daemon is expected to return the same pointer when
responding. However, a malicious daemon can send arbitrary pointer values.

Fix this by introducing find_get_vcc() which validates the pointer by
searching through vcc_hash (similar to how sigd_close() iterates over
all VCCs), and acquires a reference via sock_hold() if found.

Since struct atm_vcc embeds struct sock as its first member, they share
the same lifetime. Therefore using sock_hold/sock_put is sufficient to
keep the vcc alive while it is being used.

Note that there may be a race with sigd_close() which could mark the vcc
with various flags (e.g., ATM_VF_RELEASED) after find_get_vcc() returns.
However, sock_hold() guarantees the memory remains valid, so this race
only affects the logical state, not memory safety.

[1]: https://gist.github.com/mrpre/1ba5949c45529c511152e2f4c755b0f3

🎖@cveNotify

🚨 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