| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| Improper Neutralization of Special Elements used in an SQL Command ('SQL Injection') vulnerability in DRD Fleet Leasing DRDrive allows SQL Injection.
This issue affects DRDrive: before 20231006. |
| Improper Neutralization of Special Elements used in an SQL Command ('SQL Injection') vulnerability in ArslanSoft Education Portal allows SQL Injection.
This issue affects Education Portal: before v1.1. |
| NLnet Labs Unbound up to and including version 1.25.0 has a denial of service vulnerability in the DNSSEC validator that can lead to a crash given malicious upstream replies. When Unbound constructs chase-reply messages for validation, the code uses the wrong counter to calculate write offsets for ADDITIONAL section rrsets. DNAME duplication could increase the ANSWER section count and authority filtering could decrease the AUTHORITY section count and create an uninitialized array slot. Combining these two, the validator later dereferences this uninitialized pointer, causing an immediate process crash. An adversary controlling a DNSSEC-signed domain can trigger this bug with a single query by configuring a DNAME chain with unsigned CNAMEs and a response containing unsigned AUTHORITY records alongside signed ADDITIONAL glue records. Unbound 1.25.1 contains a patch with a fix to use the proper counters to calculate the write offsets. |
| In the Linux kernel, the following vulnerability has been resolved:
fs: ntfs3: fix infinite loop in attr_load_runs_range on inconsistent metadata
We found an infinite loop bug in the ntfs3 file system that can lead to a
Denial-of-Service (DoS) condition.
A malformed NTFS image can cause an infinite loop when an attribute header
indicates an empty run list, while directory entries reference it as
containing actual data. In NTFS, setting evcn=-1 with svcn=0 is a valid way
to represent an empty run list, and run_unpack() correctly handles this by
checking if evcn + 1 equals svcn and returning early without parsing any run
data. However, this creates a problem when there is metadata inconsistency,
where the attribute header claims to be empty (evcn=-1) but the caller
expects to read actual data. When run_unpack() immediately returns success
upon seeing this condition, it leaves the runs_tree uninitialized with
run->runs as a NULL. The calling function attr_load_runs_range() assumes
that a successful return means that the runs were loaded and sets clen to 0,
expecting the next run_lookup_entry() call to succeed. Because runs_tree
remains uninitialized, run_lookup_entry() continues to fail, and the loop
increments vcn by zero (vcn += 0), leading to an infinite loop.
This patch adds a retry counter to detect when run_lookup_entry() fails
consecutively after attr_load_runs_vcn(). If the run is still not found on
the second attempt, it indicates corrupted metadata and returns -EINVAL,
preventing the Denial-of-Service (DoS) vulnerability. |
| In the Linux kernel, the following vulnerability has been resolved:
netfilter: nf_conntrack_sip: fix use of uninitialized rtp_addr in process_sdp
process_sdp() declares union nf_inet_addr rtp_addr on the stack and
passes it to the nf_nat_sip sdp_session hook after walking the SDP
media descriptions. However rtp_addr is only initialized inside the
media loop when a recognized media type with a non-zero port is found.
If the SDP body contains no m= lines, only inactive media sections
(m=audio 0 ...) or only unrecognized media types, rtp_addr is never
assigned. Despite that, the function still calls hooks->sdp_session()
with &rtp_addr, causing nf_nat_sdp_session() to format the stale stack
value as an IP address and rewrite the SDP session owner and connection
lines with it.
With CONFIG_INIT_STACK_ALL_ZERO (default on most distributions) this
results in the session-level o= and c= addresses being rewritten to
0.0.0.0 for inactive SDP sessions. Without stack auto-init the
rewritten address is whatever happened to be on the stack.
Fix this by pre-initializing rtp_addr from the session-level connection
address (caddr) when available, and tracking via a have_rtp_addr flag
whether any valid address was established. Skip the sdp_session hook
entirely when no valid address exists. |
| In the Linux kernel, the following vulnerability has been resolved:
netfilter: nfnetlink_log: fix uninitialized padding leak in NFULA_PAYLOAD
__build_packet_message() manually constructs the NFULA_PAYLOAD netlink
attribute using skb_put() and skb_copy_bits(), bypassing the standard
nla_reserve()/nla_put() helpers. While nla_total_size(data_len) bytes
are allocated (including NLA alignment padding), only data_len bytes
of actual packet data are copied. The trailing nla_padlen(data_len)
bytes (1-3 when data_len is not 4-byte aligned) are never initialized,
leaking stale heap contents to userspace via the NFLOG netlink socket.
Replace the manual attribute construction with nla_reserve(), which
handles the tailroom check, header setup, and padding zeroing via
__nla_reserve(). The subsequent skb_copy_bits() fills in the payload
data on top of the properly initialized attribute. |
| CtrlPanel is open-source billing software for hosting providers. Versions 1.1.1 and prior contain a Stored Cross-Site Scripting (XSS) vulnerability exists in the admin role management interface. In app/Http/Controllers/Admin/RoleController.php, the datatable() method interpolates $role->name and $role->color directly into a <span> element's HTML and style attribute without sanitization, and the chained .rawColumns(['actions', 'name']) call instructs DataTables to render the name column as raw HTML, bypassing automatic output escaping. An admin with role creation or edit permissions can inject a payload such as <img src=x onerror="alert('XSS_POC')"> into the name or color fields, which is persisted to the database and executes in the browser of every admin who loads the /admin/roles page. This enables session hijacking via cookie theft, credential harvesting through fake login prompts or keyloggers, lateral privilege escalation by performing admin actions on behalf of victims, and a persistent backdoor that re-executes on every page load until the malicious role record is removed. This issue has been resolved in version 1.2.0. |
| 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 |
| Adobe Commerce versions 2.4.9-beta1, 2.4.8-p4, 2.4.7-p9, 2.4.6-p14, 2.4.5-p16, 2.4.4-p17 and earlier are affected by an Incorrect Authorization vulnerability that could result in a Security feature bypass. An attacker could leverage this vulnerability to bypass security measures and gain unauthorized write access. Exploitation of this issue does not require user interaction. |
| Adobe Commerce versions 2.4.9-beta1, 2.4.8-p4, 2.4.7-p9, 2.4.6-p14, 2.4.5-p16, 2.4.4-p17 and earlier are affected by an Incorrect Authorization vulnerability that could result in a Security feature bypass. An attacker could leverage this vulnerability to bypass security measures and gain unauthorized write access. Exploitation of this issue does not require user interaction. |
| The Read More & Accordion plugin for WordPress is vulnerable to time-based blind SQL Injection via the 'orderby' parameter in all versions up to, and including, 3.5.7. This is due to the use of esc_sql() without surrounding the value in quotes in an ORDER BY clause inside the getAllDataByLimit() and getAccordionAllDataByLimit() functions in ReadMoreData.php. The user-supplied $_GET['orderby'] value is only processed through esc_attr() (an HTML-escaping function) before being passed to these database functions, where esc_sql() is applied but the value is directly concatenated—unquoted—into the ORDER BY fragment of the SQL query before $wpdb->prepare() is called. Because esc_sql() only escapes quote characters and backslashes (which are irrelevant in an unquoted ORDER BY context), an attacker can inject arbitrary SQL expressions such as (SELECT SLEEP(5)) or conditional subqueries to perform time-based blind data extraction. This makes it possible for authenticated attackers with administrator-level access or above (or any role explicitly permitted access to the plugin's admin pages via the yrm-user-roles setting) to extract sensitive data from the database, including administrator credential hashes. |
| The Xpro Addons — 140+ Widgets for Elementor plugin for WordPress is vulnerable to unauthorized modification of data due to a missing capability check on the get_content_editor function in all versions up to, and including, 1.5.0. This makes it possible for unauthenticated attackers to create published Xpro templates. |
| 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:
smb: server: fix use-after-free in smb2_open()
The opinfo pointer obtained via rcu_dereference(fp->f_opinfo) is
dereferenced after rcu_read_unlock(), creating a use-after-free
window. |
| 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 |
| BillaBear (all versions prior to Jan 2026) contains a SQL Injection vulnerability in the EventRepository. User-controlled input from metric filter names and aggregation properties is directly interpolated into SQL queries using sprintf() without proper sanitization or identifier quoting. Although filter values are parameterized, the filter identifiers (keys) are not. An authenticated attacker with ROLE_ACCOUNT_MANAGER permissions can exploit this to execute arbitrary SQL commands. |
| In the Linux kernel, the following vulnerability has been resolved:
btrfs: log new dentries when logging parent dir of a conflicting inode
If we log the parent directory of a conflicting inode, we are not logging
the new dentries of the directory, so when we finish we have the parent
directory's inode marked as logged but we did not log its new dentries.
As a consequence if the parent directory is explicitly fsynced later and
it does not have any new changes since we logged it, the fsync is a no-op
and after a power failure the new dentries are missing.
Example scenario:
$ mkdir foo
$ sync
$rmdir foo
$ mkdir dir1
$ mkdir dir2
# A file with the same name and parent as the directory we just deleted
# and was persisted in a past transaction. So the deleted directory's
# inode is a conflicting inode of this new file's inode.
$ touch foo
$ ln foo dir2/link
# The fsync on dir2 will log the parent directory (".") because the
# conflicting inode (deleted directory) does not exists anymore, but it
# it does not log its new dentries (dir1).
$ xfs_io -c "fsync" dir2
# This fsync on the parent directory is no-op, since the previous fsync
# logged it (but without logging its new dentries).
$ xfs_io -c "fsync" .
<power failure>
# After log replay dir1 is missing.
Fix this by ensuring we log new dir dentries whenever we log the parent
directory of a no longer existing conflicting inode.
A test case for fstests will follow soon. |
| Missing Authorization vulnerability in ADD-ONS.ORG PDF for Elementor Forms + Drag And Drop Template Builder allows Exploiting Incorrectly Configured Access Control Security Levels.
This issue affects PDF for Elementor Forms + Drag And Drop Template Builder: from n/a through 5.5.1. |
| In the Linux kernel, the following vulnerability has been resolved:
spi: fix statistics allocation
The controller per-cpu statistics is not allocated until after the
controller has been registered with driver core, which leaves a window
where accessing the sysfs attributes can trigger a NULL-pointer
dereference.
Fix this by moving the statistics allocation to controller allocation
while tying its lifetime to that of the controller (rather than using
implicit devres). |
| In the Linux kernel, the following vulnerability has been resolved:
spi: fix use-after-free on controller registration failure
Make sure to deregister from driver core also in the unlikely event that
per-cpu statistics allocation fails during controller registration to
avoid use-after-free (of driver resources) and unclocked register
accesses. |
