| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| NVIDIA Triton Inference Server contains a vulnerability where an attacker could cause a path traversal issue. A successful exploit of this vulnerability might lead to denial of service. |
| NVIDIA Triton Inference Server contains a vulnerability where an attacker could cause an integer overflow. A successful exploit of this vulnerability might lead to denial of service. |
| NVIDIA Triton Inference Server contains a vulnerability in the DALI backend where an attacker could cause an out-of-bounds read. A successful exploit of this vulnerability might lead to code execution, data tampering, denial of service, or information disclosure. |
| The Account Switcher plugin for WordPress is vulnerable to Privilege Escalation in all versions up to, and including, 1.0.2. This is due to the `rememberLogin` REST API endpoint using a loose comparison (`!=` instead of `!==`) for secret validation at `app/RestAPI.php:111`, combined with no validation that the secret is non-empty. When a target user has never used the "Remember me" feature, their `asSecret` user meta does not exist, causing `get_user_meta()` to return an empty string. An attacker can send an empty `secret` parameter, which passes the comparison (`'' != ''` is `false`), and the endpoint then calls `wp_set_auth_cookie()` for the target user. Additionally, all REST routes use `permission_callback => '__return_true'` with no capability checks. This makes it possible for authenticated attackers, with Subscriber-level access and above, to switch to any user account including Administrator, ultimately granting themselves full administrative privileges. |
| NVIDIA Triton Inference Server contains a vulnerability in the DALI backend where an attacker could cause an integer overflow. A successful exploit of this vulnerability might lead to code execution, data tampering, or denial of service. |
| 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 Uncontrolled Resource Consumption vulnerability that could lead to application denial-of-service. An attacker could exploit this vulnerability to exhaust system resources, resulting in an application denial-of-service condition. 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 Uncontrolled Resource Consumption vulnerability that could lead to application denial-of-service. An attacker could exploit this vulnerability to exhaust system resources, resulting in an application denial-of-service condition. 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 a Dependency on Vulnerable Third-Party Component vulnerability that could result in an application denial-of-service. An attacker could exploit this vulnerability to crash the application, leading to a denial-of-service condition. Exploitation of this issue does not require user interaction. |
| An authorization vulnerability exists in Innoshop 0.6.0. After logging into the frontend, an attacker can directly access backend application interfaces, leading to further dangerous operations. |
| 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:
net-shapers: don't free reply skb after genlmsg_reply()
genlmsg_reply() hands the reply skb to netlink, and
netlink_unicast() consumes it on all return paths, whether the
skb is queued successfully or freed on an error path.
net_shaper_nl_get_doit() and net_shaper_nl_cap_get_doit()
currently jump to free_msg after genlmsg_reply() fails and call
nlmsg_free(msg), which can hit the same skb twice.
Return the genlmsg_reply() error directly and keep free_msg
only for pre-reply failures. |
| In the Linux kernel, the following vulnerability has been resolved:
hwmon: (pmbus/q54sj108a2) fix stack overflow in debugfs read
The q54sj108a2_debugfs_read function suffers from a stack buffer overflow
due to incorrect arguments passed to bin2hex(). The function currently
passes 'data' as the destination and 'data_char' as the source.
Because bin2hex() converts each input byte into two hex characters, a
32-byte block read results in 64 bytes of output. Since 'data' is only
34 bytes (I2C_SMBUS_BLOCK_MAX + 2), this writes 30 bytes past the end
of the buffer onto the stack.
Additionally, the arguments were swapped: it was reading from the
zero-initialized 'data_char' and writing to 'data', resulting in
all-zero output regardless of the actual I2C read.
Fix this by:
1. Expanding 'data_char' to 66 bytes to safely hold the hex output.
2. Correcting the bin2hex() argument order and using the actual read count.
3. Using a pointer to select the correct output buffer for the final
simple_read_from_buffer call. |
| 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 Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal') vulnerability that could result in arbitrary file system read and write. An authenticated attacker with administrative privileges could exploit this vulnerability to read or write files outside the restricted directory. Exploitation of this issue does not require user interaction. Scope is changed. |
| 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:
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. |
| AGL agl-service-can-low-level thru 17.1.12 contains a stack buffer overflow in the uds-c library. The send_diagnostic_request function in uds.c allocates a 6-byte stack buffer (MAX_DIAGNOSTIC_PAYLOAD_SIZE=6) but copies up to 7 bytes (MAX_UDS_REQUEST_PAYLOAD_LENGTH=7) via memcpy at an offset of 1+pid_length (2-3 bytes), resulting in 1-4 bytes of controlled stack overflow. The payload_length field (uint8_t) has no bounds check against the destination buffer. On 32-bit ARM automotive ECUs without stack canaries, this can lead to return address overwrite and RCE. |
| Buffer overflow vulnerability in Open Vehicle Monitoring System 3 (OVMS3) 3.3.005. In canformat_pcap.cpp , the parser's phdr.len field is not properly validated, allowing remote attackers to cause a denial of service or possibly execute arbitrary code via crafted PCAP input. |
| Buffer overflow vulnerability in Open Vehicle Monitoring System 3 (OVMS3) 3.3.005. In canformat_canswitch.cpp the parser does not properly validate a CANswitch DLC value, allowing remote attackers to cause a denial of service or possibly execute arbitrary code via crafted CANswitch frames. |
| 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). |
| CtrlPanel is open-source billing software for hosting providers. Versions 1.1.1 and prior contains a broken access control vulnerability where multiple admin controllers enforce permission checks on form display methods but omit equivalent checks on the corresponding write methods, allowing any authenticated user to bypass RBAC via direct POST/PATCH requests. Controllers missing checks on write methods store() and update() include ApplicationApiController (admin.api.write), CouponController (admin.coupons.write), PartnerController (admin.partners.write), ShopProductController (admin.store.write), UsefulLinkController (admin.useful_links.write), and VoucherController (admin.voucher.write); ProductController (admin.products.edit), ServerController (write/change_owner/change_identifier), and UserController (write/change_email/change_credits/change_username/change_password/change_role/change_referral/change_ptero/change_serverlimit) are missing checks on update() only, and ActivityLogController exposed empty stub store()/update() methods that silently accepted any request. An authenticated attacker without admin write privileges can issue API credentials, generate unlimited coupons and vouchers, assign arbitrary partner commission and discount rates, alter shop product pricing and limits, reassign server ownership or identifiers, and modify user accounts including roles, credits, passwords, and linked Pterodactyl IDs to achieve full privilege escalation, as well as abuse logBackIn() without the login_as permission to interfere with admin impersonation sessions. This issue has been fixed in version 1.2.0. |