| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| Concrete CMS 9.5.0 and below does not validate a CSRF token before processing requests to /dashboard/extend/update/prepare_remote_upgrade/<remoteMPID>. An attacker who controls the remote package returned for a known marketplace item ID can overwrite the package PHP on disk and force its upgrade() method to execute in a single browser navigation. This results in remote code execution as the web server user. In order to be vulnerable, the victim must be passing canInstallPackages, victim site must be connected to the Concrete marketplace; and the attacker controls the package returned for a marketplace item ID already installed on the victim site. The Concrete CMS security team gave this vulnerability a CVSS v.4.0 score of 7.5 with vector CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N. Thanks https://github.com/maru1009 for reporting. |
| Concrete CMS 9.5.0 and below emits a CSRF token in the local_available_update.php view ($token->output('do_update')) but the corresponding do_update() method in concrete/controllers/single_page/dashboard/system/update/update.php never calls $this->token->validate('do_update'). The form is rendered as a POST form, meaning the token reaches the browser, but because the controller discards it without verification, an attacker can craft a cross-site POST that triggers a core CMS update to an attacker-specified version string. In order to be vulnerable, theictim must be passing canUpgrade()anda valid update version must be present under DIR_CORE_UPDATES. The Concrete CMS security team gave this vulnerability a CVSS v.4.0 score of 7.5 with vector CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N. Thanks https://github.com/maru1009 for reporting. |
| In the Linux kernel, the following vulnerability has been resolved:
sched_ext: Fix starvation of scx_enable() under fair-class saturation
During scx_enable(), the READY -> ENABLED task switching loop changes the
calling thread's sched_class from fair to ext. Since fair has higher
priority than ext, saturating fair-class workloads can indefinitely starve
the enable thread, hanging the system. This was introduced when the enable
path switched from preempt_disable() to scx_bypass() which doesn't protect
against fair-class starvation. Note that the original preempt_disable()
protection wasn't complete either - in partial switch modes, the calling
thread could still be starved after preempt_enable() as it may have been
switched to ext class.
Fix it by offloading the enable body to a dedicated system-wide RT
(SCHED_FIFO) kthread which cannot be starved by either fair or ext class
tasks. scx_enable() lazily creates the kthread on first use and passes the
ops pointer through a struct scx_enable_cmd containing the kthread_work,
then synchronously waits for completion.
The workfn runs on a different kthread from sch->helper (which runs
disable_work), so it can safely flush disable_work on the error path
without deadlock. |
| OpenClaw version 2026.2.22 prior to 2026.2.23 contains an arbitrary code execution vulnerability in shell-env that allows attackers to execute attacker-controlled binaries by exploiting trusted-prefix fallback logic for the $SHELL variable. An attacker can influence the $SHELL environment variable on systems with writable trusted-prefix directories such as /opt/homebrew/bin to execute arbitrary binaries in the OpenClaw process context. |
| OpenS100 (the reference implementation S-100 viewer) prior to commit 753cf29 contains a remote code execution vulnerability via an unrestricted Lua interpreter. The Portrayal Engine initializes Lua using luaL_openlibs() without sandboxing or capability restrictions, exposing standard libraries such as 'os' and 'io' to untrusted portrayal catalogues. An attacker can provide a malicious S-100 portrayal catalogue containing Lua scripts that execute arbitrary commands with the privileges of the OpenS100 process when a user imports the catalogue and loads a chart. |
| In the Linux kernel, the following vulnerability has been resolved:
sched/mmcid: Prevent CID stalls due to concurrent forks
A newly forked task is accounted as MMCID user before the task is visible
in the process' thread list and the global task list. This creates the
following problem:
CPU1 CPU2
fork()
sched_mm_cid_fork(tnew1)
tnew1->mm.mm_cid_users++;
tnew1->mm_cid.cid = getcid()
-> preemption
fork()
sched_mm_cid_fork(tnew2)
tnew2->mm.mm_cid_users++;
// Reaches the per CPU threshold
mm_cid_fixup_tasks_to_cpus()
for_each_other(current, p)
....
As tnew1 is not visible yet, this fails to fix up the already allocated CID
of tnew1. As a consequence a subsequent schedule in might fail to acquire a
(transitional) CID and the machine stalls.
Move the invocation of sched_mm_cid_fork() after the new task becomes
visible in the thread and the task list to prevent this.
This also makes it symmetrical vs. exit() where the task is removed as CID
user before the task is removed from the thread and task lists. |
| PyTorch Lightning is a deep learning framework to pretrain and finetune AI models. Versions 2.6.2 and 2.6.2 have introduced functionality consistent with a credential harvesting mechanism. |
| In the Linux kernel, the following vulnerability has been resolved:
firmware: stratix10-rsu: Fix NULL pointer dereference when RSU is disabled
When the Remote System Update (RSU) isn't enabled in the First Stage
Boot Loader (FSBL), the driver encounters a NULL pointer dereference when
excute svc_normal_to_secure_thread() thread, resulting in a kernel panic:
Unable to handle kernel NULL pointer dereference at virtual address 0000000000000008
Mem abort info:
...
Data abort info:
...
[0000000000000008] user address but active_mm is swapper
Internal error: Oops: 0000000096000004 [#1] SMP
Modules linked in:
CPU: 0 UID: 0 PID: 79 Comm: svc_smc_hvc_thr Not tainted 6.19.0-rc8-yocto-standard+ #59 PREEMPT
Hardware name: SoCFPGA Stratix 10 SoCDK (DT)
pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : svc_normal_to_secure_thread+0x38c/0x990
lr : svc_normal_to_secure_thread+0x144/0x990
...
Call trace:
svc_normal_to_secure_thread+0x38c/0x990 (P)
kthread+0x150/0x210
ret_from_fork+0x10/0x20
Code: 97cfc113 f9400260 aa1403e1 f9400400 (f9400402)
---[ end trace 0000000000000000 ]---
The issue occurs because rsu_send_async_msg() fails when RSU is not enabled
in firmware, causing the channel to be freed via stratix10_svc_free_channel().
However, the probe function continues execution and registers
svc_normal_to_secure_thread(), which subsequently attempts to access the
already-freed channel, triggering the NULL pointer dereference.
Fix this by properly cleaning up the async client and returning early on
failure, preventing the thread from being used with an invalid channel. |
| In the Linux kernel, the following vulnerability has been resolved:
ASoC: qcom: qdsp6: Fix q6apm remove ordering during ADSP stop and start
During ADSP stop and start, the kernel crashes due to the order in which
ASoC components are removed.
On ADSP stop, the q6apm-audio .remove callback unloads topology and removes
PCM runtimes during ASoC teardown. This deletes the RTDs that contain the
q6apm DAI components before their removal pass runs, leaving those
components still linked to the card and causing crashes on the next rebind.
Fix this by ensuring that all dependent (child) components are removed
first, and the q6apm component is removed last.
[ 48.105720] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000d0
[ 48.114763] Mem abort info:
[ 48.117650] ESR = 0x0000000096000004
[ 48.121526] EC = 0x25: DABT (current EL), IL = 32 bits
[ 48.127010] SET = 0, FnV = 0
[ 48.130172] EA = 0, S1PTW = 0
[ 48.133415] FSC = 0x04: level 0 translation fault
[ 48.138446] Data abort info:
[ 48.141422] ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000
[ 48.147079] CM = 0, WnR = 0, TnD = 0, TagAccess = 0
[ 48.152354] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
[ 48.157859] user pgtable: 4k pages, 48-bit VAs, pgdp=00000001173cf000
[ 48.164517] [00000000000000d0] pgd=0000000000000000, p4d=0000000000000000
[ 48.171530] Internal error: Oops: 0000000096000004 [#1] SMP
[ 48.177348] Modules linked in: q6prm_clocks q6apm_lpass_dais q6apm_dai snd_q6dsp_common q6prm snd_q6apm 8021q garp mrp stp llc snd_soc_hdmi_codec apr pdr_interface phy_qcom_edp fastrpc qcom_pd_mapper rpmsg_ctrl qrtr_smd rpmsg_char qcom_pdr_msg qcom_iris v4l2_mem2mem videobuf2_dma_contig ath11k_pci msm ubwc_config at24 ath11k videobuf2_memops mac80211 ocmem videobuf2_v4l2 libarc4 drm_gpuvm mhi qrtr videodev drm_exec snd_soc_sc8280xp gpu_sched videobuf2_common nvmem_qcom_spmi_sdam snd_soc_qcom_sdw drm_dp_aux_bus qcom_q6v5_pas qcom_spmi_temp_alarm snd_soc_qcom_common rtc_pm8xxx qcom_pon drm_display_helper cec qcom_pil_info qcom_stats soundwire_bus drm_client_lib mc dispcc0_sa8775p videocc_sa8775p qcom_q6v5 camcc_sa8775p snd_soc_dmic phy_qcom_sgmii_eth snd_soc_max98357a i2c_qcom_geni snd_soc_core dwmac_qcom_ethqos llcc_qcom icc_bwmon qcom_sysmon snd_compress qcom_refgen_regulator coresight_stm stmmac_platform snd_pcm_dmaengine qcom_common coresight_tmc stmmac coresight_replicator qcom_glink_smem coresight_cti stm_core
[ 48.177444] coresight_funnel snd_pcm ufs_qcom phy_qcom_qmp_usb gpi phy_qcom_snps_femto_v2 coresight phy_qcom_qmp_ufs qcom_wdt gpucc_sa8775p pcs_xpcs mdt_loader qcom_ice icc_osm_l3 qmi_helpers snd_timer snd soundcore display_connector qcom_rng nvmem_reboot_mode drm_kms_helper phy_qcom_qmp_pcie sha256 cfg80211 rfkill socinfo fuse drm backlight ipv6
[ 48.301059] CPU: 2 UID: 0 PID: 293 Comm: kworker/u32:2 Not tainted 6.19.0-rc6-dirty #10 PREEMPT
[ 48.310081] Hardware name: Qualcomm Technologies, Inc. Lemans EVK (DT)
[ 48.316782] Workqueue: pdr_notifier_wq pdr_notifier_work [pdr_interface]
[ 48.323672] pstate: 20400005 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[ 48.330825] pc : mutex_lock+0xc/0x54
[ 48.334514] lr : soc_dapm_shutdown_dapm+0x44/0x174 [snd_soc_core]
[ 48.340794] sp : ffff800084ddb7b0
[ 48.344207] x29: ffff800084ddb7b0 x28: ffff00009cd9cf30 x27: ffff00009cd9cc00
[ 48.351544] x26: ffff000099610190 x25: ffffa31d2f19c810 x24: ffffa31d2f185098
[ 48.358869] x23: ffff800084ddb7f8 x22: 0000000000000000 x21: 00000000000000d0
[ 48.366198] x20: ffff00009ba6c338 x19: ffff00009ba6c338 x18: 00000000ffffffff
[ 48.373528] x17: 000000040044ffff x16: ffffa31d4ae6dca8 x15: 072007740775076f
[ 48.380853] x14: 0765076d07690774 x13: 00313a323a656369 x12: 767265733a637673
[ 48.388182] x11: 00000000000003f9 x10: ffffa31d4c7dea98 x9 : 0000000000000001
[ 48.395519] x8 : ffff00009a2aadc0 x7 : 0000000000000003 x6 : 0000000000000000
[ 48.402854] x5 : 0000000000000
---truncated--- |
| Use after free in Extensions in Google Chrome on Mac prior to 148.0.7778.168 allowed an attacker who convinced a user to install a malicious extension to execute arbitrary code via a crafted Chrome Extension. (Chromium security severity: Medium) |
| In the Linux kernel, the following vulnerability has been resolved:
iavf: fix PTP use-after-free during reset
Commit 7c01dbfc8a1c5f ("iavf: periodically cache PHC time") introduced a
worker to cache PHC time, but failed to stop it during reset or disable.
This creates a race condition where `iavf_reset_task()` or
`iavf_disable_vf()` free adapter resources (AQ) while the worker is still
running. If the worker triggers `iavf_queue_ptp_cmd()` during teardown, it
accesses freed memory/locks, leading to a crash.
Fix this by calling `iavf_ptp_release()` before tearing down the adapter.
This ensures `ptp_clock_unregister()` synchronously cancels the worker and
cleans up the chardev before the backing resources are destroyed. |
| Use after free in WebRTC in Google Chrome on Linux prior to 148.0.7778.179 allowed a remote attacker to execute arbitrary code via a crafted HTML page. (Chromium security severity: Critical) |
| Use after free in GPU in Google Chrome on Windows prior to 148.0.7778.179 allowed a remote attacker to execute arbitrary code inside a sandbox via a crafted HTML page. (Chromium security severity: High) |
| Use after free in QUIC in Google Chrome on prior to 148.0.7778.179 allowed a remote attacker to execute arbitrary code inside a sandbox via malicious network traffic. (Chromium security severity: High) |
| Use after free in XR in Google Chrome on Windows prior to 148.0.7778.179 allowed a remote attacker to execute arbitrary code via a crafted HTML page. (Chromium security severity: High) |
| A use-after-return vulnerability exists in the `named` server when handling DNS queries signed with SIG(0). Using a specially-crafted DNS request, an attacker may be able to cause an ACL to improperly (mis)match an IP address. In a default-allow ACL (denying only specific IP addresses), this may lead to unauthorized access. Default-deny ACLs should fail-secure.
This issue affects BIND 9 versions 9.20.0 through 9.20.20, 9.21.0 through 9.21.19, and 9.20.9-S1 through 9.20.20-S1.
BIND 9 versions 9.18.0 through 9.18.46 and 9.18.11-S1 through 9.18.46-S1 are NOT affected. |
| A use-after-free vulnerability exists within the DNS-over-HTTPS implementation.
This issue affects BIND 9 versions 9.20.0 through 9.20.22, 9.21.0 through 9.21.21, and 9.20.9-S1 through 9.20.22-S1.
BIND 9 versions 9.18.0 through 9.18.48 and 9.18.11-S1 through 9.18.48-S1 are NOT affected. |
| 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:
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. |
