Total
36051 CVE
| CVE | Vendors | Products | Updated | CVSS v2 | CVSS v3 |
|---|---|---|---|---|---|
| CVE-2026-23466 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 7.8 HIGH |
| In the Linux kernel, the following vulnerability has been resolved: drm/xe: Open-code GGTT MMIO access protection GGTT MMIO access is currently protected by hotplug (drm_dev_enter), which works correctly when the driver loads successfully and is later unbound or unloaded. However, if driver load fails, this protection is insufficient because drm_dev_unplug() is never called. Additionally, devm release functions cannot guarantee that all BOs with GGTT mappings are destroyed before the GGTT MMIO region is removed, as some BOs may be freed asynchronously by worker threads. To address this, introduce an open-coded flag, protected by the GGTT lock, that guards GGTT MMIO access. The flag is cleared during the dev_fini_ggtt devm release function to ensure MMIO access is disabled once teardown begins. (cherry picked from commit 4f3a998a173b4325c2efd90bdadc6ccd3ad9a431) | |||||
| CVE-2026-23465 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 5.5 MEDIUM |
| 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. | |||||
| CVE-2026-31406 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 7.8 HIGH |
| 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(). | |||||
| CVE-2026-31409 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 8.8 HIGH |
| 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. | |||||
| CVE-2026-27481 | 1 Discourse | 1 Discourse | 2026-07-24 | N/A | 5.3 MEDIUM |
| Discourse is an open-source discussion platform. From versions 2026.1.0-latest to before 2026.1.3, 2026.2.0-latest to before 2026.2.2, and 2026.3.0-latest to before 2026.3.0, an authorization bypass vulnerability allows unauthenticated or unauthorized users to view hidden (staff-only) tags and its associated data. All Discourse instances with tagging enabled and staff-only tag groups configured are impacted. This issue has been patched in versions 2026.1.3, 2026.2.2, and 2026.3.0. | |||||
| CVE-2026-34080 | 1 Flatpak | 1 Xdg-dbus-proxy | 2026-07-24 | N/A | 5.5 MEDIUM |
| xdg-dbus-proxy is a filtering proxy for D-Bus connections. Prior to 0.1.7, a policy parser vulnerability allows bypassing eavesdrop restrictions. The proxy checks for eavesdrop=true in policy rules but fails to handle eavesdrop ='true' (with a space before the equals sign) and similar cases. Clients can intercept D-Bus messages they should not have access to. This vulnerability is fixed in 0.1.7. | |||||
| CVE-2026-34723 | 1 Zammad | 1 Zammad | 2026-07-24 | N/A | 7.5 HIGH |
| Zammad is a web based open source helpdesk/customer support system. Prior to 7.0.1 and 6.5.4, unauthenticated remote attackers were able to access the getting started endpoint to get access to sensitive internal entity data, even after the system setup was completed. This vulnerability is fixed in 7.0.1 and 6.5.4. | |||||
| CVE-2026-23459 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 8.2 HIGH |
| In the Linux kernel, the following vulnerability has been resolved: ip_tunnel: adapt iptunnel_xmit_stats() to NETDEV_PCPU_STAT_DSTATS Blamed commits forgot that vxlan/geneve use udp_tunnel[6]_xmit_skb() which call iptunnel_xmit_stats(). iptunnel_xmit_stats() was assuming tunnels were only using NETDEV_PCPU_STAT_TSTATS. @syncp offset in pcpu_sw_netstats and pcpu_dstats is different. 32bit kernels would either have corruptions or freezes if the syncp sequence was overwritten. This patch also moves pcpu_stat_type closer to dev->{t,d}stats to avoid a potential cache line miss since iptunnel_xmit_stats() needs to read it. | |||||
| CVE-2026-39410 | 1 Hono | 1 Hono | 2026-07-24 | N/A | 4.8 MEDIUM |
| Hono is a Web application framework that provides support for any JavaScript runtime. Prior to 4.12.12, a discrepancy between browser cookie parsing and parse() handling allows cookie prefix protections to be bypassed. Cookie names that are treated as distinct by the browser may be normalized to the same key by parse(), allowing attacker-controlled cookies to override legitimate ones. This vulnerability is fixed in 4.12.12. | |||||
| CVE-2026-23429 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 7.8 HIGH |
| In the Linux kernel, the following vulnerability has been resolved: iommu/sva: Fix crash in iommu_sva_unbind_device() domain->mm->iommu_mm can be freed by iommu_domain_free(): iommu_domain_free() mmdrop() __mmdrop() mm_pasid_drop() After iommu_domain_free() returns, accessing domain->mm->iommu_mm may dereference a freed mm structure, leading to a crash. Fix this by moving the code that accesses domain->mm->iommu_mm to before the call to iommu_domain_free(). | |||||
| CVE-2026-39412 | 1 Liquidjs | 1 Liquidjs | 2026-07-24 | N/A | 5.3 MEDIUM |
| LiquidJS is a Shopify / GitHub Pages compatible template engine in pure JavaScript. Prior to 10.25.4, the sort_natural filter bypasses the ownPropertyOnly security option, allowing template authors to extract values of prototype-inherited properties through a sorting side-channel attack. Applications relying on ownPropertyOnly: true as a security boundary (e.g., multi-tenant template systems) are exposed to information disclosure of sensitive prototype properties such as API keys and tokens. This vulnerability is fixed in 10.25.4. | |||||
| CVE-2026-40068 | 1 Anthropic | 1 Claude Code | 2026-07-24 | N/A | 8.8 HIGH |
| In versions 2.1.63 through 2.1.83 of Claude Code, the folder trust determination logic used the git worktree commondir file without validating its contents. An attacker could craft a malicious repository with a commondir file pointing to a path the victim had previously trusted, causing Claude Code to bypass its trust confirmation dialog and immediately execute hooks defined in `.claude/settings.json`. Exploitation requires the victim to clone the malicious repository and run Claude Code within it, and the attacker must know or guess a path the victim had already trusted. This issue has been fixed in version 2.1.84. | |||||
| CVE-2026-35533 | 1 Jdx | 1 Mise | 2026-07-24 | N/A | 7.7 HIGH |
| mise manages dev tools like node, python, cmake, and terraform. From 2026.2.18 through 2026.4.5, mise loads trust-control settings from a local project .mise.toml before the trust check runs. An attacker who can place a malicious .mise.toml in a repository can make that same file appear trusted and then reach dangerous directives such as [env] _.source, templates, hooks, or tasks. | |||||
| CVE-2026-35413 | 1 Monospace | 1 Directus | 2026-07-24 | N/A | 5.3 MEDIUM |
| Directus is a real-time API and App dashboard for managing SQL database content. Prior to 11.16.1, when GRAPHQL_INTROSPECTION=false is configured, Directus correctly blocks standard GraphQL introspection queries (__schema, __type). However, the server_specs_graphql resolver on the /graphql/system endpoint returns an equivalent SDL representation of the schema and was not subject to the same restriction. This allowed the introspection control to be bypassed, exposing schema structure (collection names, field names, types, and relationships) to unauthenticated users at the public permission level, and to authenticated users at their permitted permission level. This vulnerability is fixed in 11.16.1. | |||||
| CVE-2026-23436 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 5.5 MEDIUM |
| In the Linux kernel, the following vulnerability has been resolved: net: shaper: protect from late creation of hierarchy We look up a netdev during prep of Netlink ops (pre- callbacks) and take a ref to it. Then later in the body of the callback we take its lock or RCU which are the actual protections. The netdev may get unregistered in between the time we take the ref and the time we lock it. We may allocate the hierarchy after flush has already run, which would lead to a leak. Take the instance lock in pre- already, this saves us from the race and removes the need for dedicated lock/unlock callbacks completely. After all, if there's any chance of write happening concurrently with the flush - we're back to leaking the hierarchy. We may take the lock for devices which don't support shapers but we're only dealing with SET operations here, not taking the lock would be optimizing for an error case. | |||||
| CVE-2026-23434 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 7.1 HIGH |
| In the Linux kernel, the following vulnerability has been resolved: mtd: rawnand: serialize lock/unlock against other NAND operations nand_lock() and nand_unlock() call into chip->ops.lock_area/unlock_area without holding the NAND device lock. On controllers that implement SET_FEATURES via multiple low-level PIO commands, these can race with concurrent UBI/UBIFS background erase/write operations that hold the device lock, resulting in cmd_pending conflicts on the NAND controller. Add nand_get_device()/nand_release_device() around the lock/unlock operations to serialize them against all other NAND controller access. | |||||
| CVE-2026-39889 | 1 Praison | 1 Praisonai | 2026-07-24 | N/A | 7.5 HIGH |
| PraisonAI is a multi-agent teams system. Prior to 4.5.115, the A2U (Agent-to-User) event stream server in PraisonAI exposes all agent activity without authentication. The create_a2u_routes() function registers the following endpoints with NO authentication checks: /a2u/info, /a2u/subscribe, /a2u/events/{stream_name}, /a2u/events/sub/{id}, and /a2u/health. This vulnerability is fixed in 4.5.115. | |||||
| CVE-2026-23445 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 7.8 HIGH |
| In the Linux kernel, the following vulnerability has been resolved: igc: fix page fault in XDP TX timestamps handling If an XDP application that requested TX timestamping is shutting down while the link of the interface in use is still up the following kernel splat is reported: [ 883.803618] [ T1554] BUG: unable to handle page fault for address: ffffcfb6200fd008 ... [ 883.803650] [ T1554] Call Trace: [ 883.803652] [ T1554] <TASK> [ 883.803654] [ T1554] igc_ptp_tx_tstamp_event+0xdf/0x160 [igc] [ 883.803660] [ T1554] igc_tsync_interrupt+0x2d5/0x300 [igc] ... During shutdown of the TX ring the xsk_meta pointers are left behind, so that the IRQ handler is trying to touch them. This issue is now being fixed by cleaning up the stale xsk meta data on TX shutdown. TX timestamps on other queues remain unaffected. | |||||
| CVE-2026-23421 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 5.5 MEDIUM |
| In the Linux kernel, the following vulnerability has been resolved: drm/xe/configfs: Free ctx_restore_mid_bb in release ctx_restore_mid_bb memory is allocated in wa_bb_store(), but xe_config_device_release() only frees ctx_restore_post_bb. Free ctx_restore_mid_bb[0].cs as well to avoid leaking the allocation when the configfs device is removed. (cherry picked from commit a235e7d0098337c3f2d1e8f3610c719a589e115f) | |||||
| CVE-2026-34406 | 1 Aptrs | 1 Aptrs | 2026-07-24 | N/A | 8.8 HIGH |
| APTRS (Automated Penetration Testing Reporting System) is a Python and Django-based automated reporting tool designed for penetration testers and security organizations. Prior to version 2.0.1, the edit_user endpoint (POST /api/auth/edituser/<pk>) allows Any user who can reach that endpoint and submit crafted permission to escalate their own account (or any other account) to superuser by including "is_superuser": true in the request body. The root cause is that CustomUserSerializer explicitly includes is_superuser in its fields list but omits it from read_only_fields, making it a writable field. The edit_user view performs no additional validation to prevent non-superusers from modifying this field. Once is_superuser is set to true, gaining unrestricted access to all application functionality without requiring re-authentication. This issue has been patched in version 2.0.1. | |||||