| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| HCL BigFix Service Management (SM) is affected by a security misconfiguration due to a missing or insecure “X-Content-Type-Options” header. This could allow browsers to perform MIME-type sniffing, potentially causing malicious content to be interpreted and executed incorrectly. |
| In the Linux kernel, the following vulnerability has been resolved:
spi: amlogic: spifc-a4: Fix DMA mapping error handling
Fix three bugs in aml_sfc_dma_buffer_setup() error paths:
1. Unnecessary goto: When the first DMA mapping (sfc->daddr) fails,
nothing needs cleanup. Use direct return instead of goto.
2. Double-unmap bug: When info DMA mapping failed, the code would
unmap sfc->daddr inline, then fall through to out_map_data which
would unmap it again, causing a double-unmap.
3. Wrong unmap size: The out_map_info label used datalen instead of
infolen when unmapping sfc->iaddr, which could lead to incorrect
DMA sync behavior. |
| In the Linux kernel, the following vulnerability has been resolved:
net: spacemit: Fix error handling in emac_tx_mem_map()
The DMA mappings were leaked on mapping error. Free them with the
existing emac_free_tx_buf() function. |
| In the Linux kernel, the following vulnerability has been resolved:
iio: chemical: sps30_i2c: fix buffer size in sps30_i2c_read_meas()
sizeof(num) evaluates to sizeof(size_t) (8 bytes on 64-bit) instead
of the intended __be32 element size (4 bytes). Use sizeof(*meas) to
correctly match the buffer element type. |
| In the Linux kernel, the following vulnerability has been resolved:
netfilter: nf_tables: Fix for duplicate device in netdev hooks
When handling NETDEV_REGISTER notification, duplicate device
registration must be avoided since the device may have been added by
nft_netdev_hook_alloc() already when creating the hook. |
| In the Linux kernel, the following vulnerability has been resolved:
mctp: route: hold key->lock in mctp_flow_prepare_output()
mctp_flow_prepare_output() checks key->dev and may call
mctp_dev_set_key(), but it does not hold key->lock while doing so.
mctp_dev_set_key() and mctp_dev_release_key() are annotated with
__must_hold(&key->lock), so key->dev access is intended to be
serialized by key->lock. The mctp_sendmsg() transmit path reaches
mctp_flow_prepare_output() via mctp_local_output() -> mctp_dst_output()
without holding key->lock, so the check-and-set sequence is racy.
Example interleaving:
CPU0 CPU1
---- ----
mctp_flow_prepare_output(key, devA)
if (!key->dev) // sees NULL
mctp_flow_prepare_output(
key, devB)
if (!key->dev) // still NULL
mctp_dev_set_key(devB, key)
mctp_dev_hold(devB)
key->dev = devB
mctp_dev_set_key(devA, key)
mctp_dev_hold(devA)
key->dev = devA // overwrites devB
Now both devA and devB references were acquired, but only the final
key->dev value is tracked for release. One reference can be lost,
causing a resource leak as mctp_dev_release_key() would only decrease
the reference on one dev.
Fix by taking key->lock around the key->dev check and
mctp_dev_set_key() call. |
| A flaw has been found in Kilo-Org kilocode up to 7.0.47. This issue affects the function Load of the file packages/opencode/src/config/config.ts of the component Environment Variable Handler. Executing a manipulation of the argument KILO_CONFIG_CONTENT can lead to information disclosure. It is possible to launch the attack remotely. The exploit has been published and may be used. The vendor was contacted early about this disclosure but did not respond in any way. |
| 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. |
| Incorrect Use of Privileged APIs vulnerability in Utarit Information Technologies SoliPay Mobile App allows Collect Data as Provided by Users.
This issue affects SoliPay Mobile App: before 5.0.8. |
| The mono package before 6.8.0.105+dfsg-3.3 for Debian allows arbitrary code execution because the application/x-ms-dos-executable MIME type is associated with an un-sandboxed Mono CLR interpreter. |
| A security issue was discovered in ingress-nginx where a combination of Ingress annotations can be used to inject configuration into nginx. This can lead to arbitrary code execution in the context of the ingress-nginx controller, and disclosure of Secrets accessible to the controller. (Note that in the default installation, the controller can access all Secrets cluster-wide.) |
| In the Linux kernel, the following vulnerability has been resolved:
dmaengine: xilinx: xdma: Fix regmap init error handling
devm_regmap_init_mmio returns an ERR_PTR() upon error, not NULL.
Fix the error check and also fix the error message. Use the error code
from ERR_PTR() instead of the wrong value in ret. |
| In the Linux kernel, the following vulnerability has been resolved:
xsk: validate MTU against usable frame size on bind
AF_XDP bind currently accepts zero-copy pool configurations without
verifying that the device MTU fits into the usable frame space provided
by the UMEM chunk.
This becomes a problem since we started to respect tailroom which is
subtracted from chunk_size (among with headroom). 2k chunk size might
not provide enough space for standard 1500 MTU, so let us catch such
settings at bind time. Furthermore, validate whether underlying HW will
be able to satisfy configured MTU wrt XSK's frame size multiplied by
supported Rx buffer chain length (that is exposed via
net_device::xdp_zc_max_segs). |
| Improper Input Validation vulnerability in Apache OFBiz.
This issue affects Apache OFBiz: before 24.09.06.
Users are recommended to upgrade to version 24.09.06, which fixes the issue. |
| Microsoft Office OneNote Remote Code Execution Vulnerability |
| Microsoft Outlook Remote Code Execution Vulnerability |
| Microsoft Excel Security Feature Bypass Vulnerability |
| Microsoft Excel Remote Code Execution Vulnerability |
| Microsoft Office Visio Remote Code Execution Vulnerability |
