Total
36333 CVE
| CVE | Vendors | Products | Updated | CVSS v2 | CVSS v3 |
|---|---|---|---|---|---|
| CVE-2026-61067 | 1 Oracle | 1 Access Manager | 2026-07-28 | N/A | 8.0 HIGH |
| Vulnerability in the Oracle Access Manager product of Oracle Fusion Middleware (component: Authentication Engine). Supported versions that are affected are 12.2.1.4.0 and 14.1.2.1.0. Easily exploitable vulnerability allows low privileged attacker with access to the physical communication segment attached to the hardware where the Oracle Access Manager executes to compromise Oracle Access Manager. Successful attacks of this vulnerability can result in takeover of Oracle Access Manager. CVSS 3.1 Base Score 8.0 (Confidentiality, Integrity and Availability impacts). CVSS Vector: (CVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H). | |||||
| CVE-2026-61065 | 1 Oracle | 1 Access Manager | 2026-07-28 | N/A | 9.8 CRITICAL |
| Vulnerability in the Oracle Access Manager product of Oracle Fusion Middleware (component: Authentication Engine). Supported versions that are affected are 12.2.1.4.0 and 14.1.2.1.0. Easily exploitable vulnerability allows unauthenticated attacker with network access via HTTP to compromise Oracle Access Manager. Successful attacks of this vulnerability can result in takeover of Oracle Access Manager. CVSS 3.1 Base Score 9.8 (Confidentiality, Integrity and Availability impacts). CVSS Vector: (CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H). | |||||
| CVE-2026-60333 | 1 Oracle | 1 Access Manager | 2026-07-28 | N/A | 9.9 CRITICAL |
| Vulnerability in the Oracle Access Manager product of Oracle Fusion Middleware (component: Authentication Engine). Supported versions that are affected are 12.2.1.4.0 and 14.1.2.1.0. Easily exploitable vulnerability allows low privileged attacker with network access via HTTP to compromise Oracle Access Manager. While the vulnerability is in Oracle Access Manager, attacks may significantly impact additional products (scope change). Successful attacks of this vulnerability can result in takeover of Oracle Access Manager. CVSS 3.1 Base Score 9.9 (Confidentiality, Integrity and Availability impacts). CVSS Vector: (CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H). | |||||
| CVE-2025-36364 | 1 Hcltech | 1 Devops Plan | 2026-07-27 | N/A | 6.2 MEDIUM |
| IBM DevOps Plan 3.0.0 through 3.0.5 allows web page cache to be stored locally which can be read by another user on the system. | |||||
| CVE-2026-60342 | 1 Oracle | 1 Access Manager | 2026-07-27 | N/A | 5.3 MEDIUM |
| Vulnerability in the Oracle Access Manager product of Oracle Fusion Middleware (component: Authentication Engine). Supported versions that are affected are 12.2.1.4.0 and 14.1.2.1.0. Easily exploitable vulnerability allows unauthenticated attacker with network access via HTTP to compromise Oracle Access Manager. Successful attacks of this vulnerability can result in unauthorized read access to a subset of Oracle Access Manager accessible data. CVSS 3.1 Base Score 5.3 (Confidentiality impacts). CVSS Vector: (CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N). | |||||
| CVE-2025-71256 | 2 Google, Unisoc | 5 Android, T8100, T8200 and 2 more | 2026-07-25 | N/A | 7.5 HIGH |
| In nr modem, there is a possible improper input validation. This could lead to remote denial of service with no additional execution privileges needed. | |||||
| CVE-2025-71251 | 2 Google, Unisoc | 17 Android, Sc7731e, Sc9832e and 14 more | 2026-07-25 | N/A | 7.5 HIGH |
| In IMS, there is a possible system crash due to improper input validation. This could lead to remote denial of service with no additional execution privileges needed. | |||||
| CVE-2025-71253 | 2 Google, Unisoc | 17 Android, Sc7731e, Sc9832e and 14 more | 2026-07-25 | N/A | 7.5 HIGH |
| In Modem IMS, there is a possible improper input validation. This could lead to remote denial of service with no additional execution privileges needed. | |||||
| CVE-2025-9577 | 1 Totolink | 2 X2000r, X2000r Firmware | 2026-07-25 | 1.0 LOW | 2.5 LOW |
| A security flaw has been discovered in TOTOLINK X2000R up to 2.0.0. The affected element is an unknown function of the file /etc/shadow.sample of the component Administrative Interface. The manipulation results in use of default credentials. Attacking locally is a requirement. Attacks of this nature are highly complex. The exploitability is described as difficult. The exploit has been released to the public and may be exploited. | |||||
| CVE-2026-27949 | 1 Plane | 1 Plane | 2026-07-24 | N/A | 2.0 LOW |
| Plane is an an open-source project management tool. Prior to 1.3.0, a vulnerability was identified in Plane's authentication flow where a user's email address is included as a query parameter in the URL during error handling (e.g., when an invalid magic code is submitted). Transmitting personally identifiable information (PII) via GET request query strings is classified as an insecure design practice. The affected code path is located in the authentication utility module (packages/utils/src/auth.ts). This vulnerability is fixed in 1.3.0. | |||||
| 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-2026-34947 | 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, staged user custom fields and username are exposed on public invite pages without email verification. This issue has been patched in versions 2026.1.3, 2026.2.2, and 2026.3.0. | |||||
| 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-2026-23457 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 8.6 HIGH |
| In the Linux kernel, the following vulnerability has been resolved: netfilter: nf_conntrack_sip: fix Content-Length u32 truncation in sip_help_tcp() sip_help_tcp() parses the SIP Content-Length header with simple_strtoul(), which returns unsigned long, but stores the result in unsigned int clen. On 64-bit systems, values exceeding UINT_MAX are silently truncated before computing the SIP message boundary. For example, Content-Length 4294967328 (2^32 + 32) is truncated to 32, causing the parser to miscalculate where the current message ends. The loop then treats trailing data in the TCP segment as a second SIP message and processes it through the SDP parser. Fix this by changing clen to unsigned long to match the return type of simple_strtoul(), and reject Content-Length values that exceed the remaining TCP payload length. | |||||
| CVE-2026-31410 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 5.5 MEDIUM |
| In the Linux kernel, the following vulnerability has been resolved: ksmbd: use volume UUID in FS_OBJECT_ID_INFORMATION Use sb->s_uuid for a proper volume identifier as the primary choice. For filesystems that do not provide a UUID, fall back to stfs.f_fsid obtained from vfs_statfs(). | |||||
| 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-2026-23474 | 1 Linux | 1 Linux Kernel | 2026-07-24 | N/A | 5.5 MEDIUM |
| In the Linux kernel, the following vulnerability has been resolved: mtd: Avoid boot crash in RedBoot partition table parser Given CONFIG_FORTIFY_SOURCE=y and a recent compiler, commit 439a1bcac648 ("fortify: Use __builtin_dynamic_object_size() when available") produces the warning below and an oops. Searching for RedBoot partition table in 50000000.flash at offset 0x7e0000 ------------[ cut here ]------------ WARNING: lib/string_helpers.c:1035 at 0xc029e04c, CPU#0: swapper/0/1 memcmp: detected buffer overflow: 15 byte read of buffer size 14 Modules linked in: CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.19.0 #1 NONE As Kees said, "'names' is pointing to the final 'namelen' many bytes of the allocation ... 'namelen' could be basically any length at all. This fortify warning looks legit to me -- this code used to be reading beyond the end of the allocation." Since the size of the dynamic allocation is calculated with strlen() we can use strcmp() instead of memcmp() and remain within bounds. | |||||
| 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-2026-23465 | 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. | |||||