CVE Watch
Every published CVE, mapped to engagement reality.
Crawled from cve.org every day. Each entry annotated with the QSearch coverage signal — how many of our agents, skills, and playbooks address the technique. Subscribe via RSS for SIEM pipe, or get the weekly digest by email.
Use after free in WebRTC in Google Chrome prior to 147.0.7727.55 allowed a remote attacker to execute arbitrary code inside a sandbox via...
Use after free in WebRTC in Google Chrome prior to 147.0.7727.55 allowed a remote attacker to execute arbitrary code inside a sandbox via a crafted HTML page. (Chromium security severity: High)
googleCWE-416A flaw was found in Red Hat Quay's handling of resumable container image layer uploads
A flaw was found in Red Hat Quay's handling of resumable container image layer uploads. The upload process stores intermediate data in the database using a format that, if tampered with, could allow an attacker to execute arbitrary code on the Quay server.
redhatCWE-502A flaw was found in Red Hat Quay's container image upload process
A flaw was found in Red Hat Quay's container image upload process. An authenticated user with push access to any repository on the registry can interfere with image uploads in progress by other users, including those in repositories they do not have access to. This could allow the attacker to read, modify, or cancel another user's in-progress image upload.
redhatCWE-639An out-of-bounds write issue in the virtio PCI transport in Firecracker 1.13.0 through 1.14.3 and 1.15.0 on x86_64 and aarch64 might allo...
An out-of-bounds write issue in the virtio PCI transport in Firecracker 1.13.0 through 1.14.3 and 1.15.0 on x86_64 and aarch64 might allow a local guest user with root privileges to crash the Firecracker VMM process or potentially execute arbitrary code on the host via modification of virtio queue configuration registers after device activation. Achieving code execution on the host requires additional preconditions, such as the use of a custom guest kernel or specific snapshot configurations. To remediate this, users should upgrade to Firecracker 1.14.4 or 1.15.1 and later.
amazonCWE-369CWE-787File Browser is a file managing interface for uploading, deleting, previewing, renaming, and editing files within a specified directory
File Browser is a file managing interface for uploading, deleting, previewing, renaming, and editing files within a specified directory. From 2.0.0 until 2.33.8, the hook system in File Browser — which executes administrator-defined shell commands on file events such as upload, rename, and delete — is vulnerable to OS command injection. Variable substitution for values like $FILE and $USERNAME is performed via os.Expand without sanitization. An attacker with file write permission can craft a malicious filename containing shell metacharacters, causing the server to execute arbitrary OS commands when the hook fires. This results in Remote Code Execution (RCE). This feature has been disabled by default for all installations from v2.33.8 onwards, including for existent installations.
filebrowserCWE-78CWE-88Memory-safety vulnerability in github.com/jackc/pgx/v5
Memory-safety vulnerability in github.com/jackc/pgx/v5.
jackcMemory-safety vulnerability in github.com/jackc/pgx/v5
Memory-safety vulnerability in github.com/jackc/pgx/v5.
jackcIn the Linux kernel, the following vulnerability has been resolved: ksmbd: unset conn->binding on failed binding request When a multich...
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.
linuxIn the Linux kernel, the following vulnerability has been resolved: Bluetooth: SCO: Fix use-after-free in sco_recv_frame() due to missin...
In the Linux kernel, the following vulnerability has been resolved: Bluetooth: SCO: Fix use-after-free in sco_recv_frame() due to missing sock_hold sco_recv_frame() reads conn->sk under sco_conn_lock() but immediately releases the lock without holding a reference to the socket. A concurrent close() can free the socket between the lock release and the subsequent sk->sk_state access, resulting in a use-after-free. Other functions in the same file (sco_sock_timeout(), sco_conn_del()) correctly use sco_sock_hold() to safely hold a reference under the lock. Fix by using sco_sock_hold() to take a reference before releasing the lock, and adding sock_put() on all exit paths.
linuxCWE-416In the Linux kernel, the following vulnerability has been resolved: netfilter: conntrack: add missing netlink policy validations Hyunwo...
In the Linux kernel, the following vulnerability has been resolved: netfilter: conntrack: add missing netlink policy validations Hyunwoo Kim reports out-of-bounds access in sctp and ctnetlink. These attributes are used by the kernel without any validation. Extend the netlink policies accordingly. Quoting the reporter: nlattr_to_sctp() assigns the user-supplied CTA_PROTOINFO_SCTP_STATE value directly to ct->proto.sctp.state without checking that it is within the valid range. [..] and: ... with exp->dir = 100, the access at ct->master->tuplehash[100] reads 5600 bytes past the start of a 320-byte nf_conn object, causing a slab-out-of-bounds read confirmed by UBSAN.
linuxCWE-787In the Linux kernel, the following vulnerability has been resolved: xfrm: Fix work re-schedule after cancel in xfrm_nat_keepalive_net_fi...
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().
linuxIn the Linux kernel, the following vulnerability has been resolved: media: dvb-net: fix OOB access in ULE extension header tables The u...
In the Linux kernel, the following vulnerability has been resolved: media: dvb-net: fix OOB access in ULE extension header tables The ule_mandatory_ext_handlers[] and ule_optional_ext_handlers[] tables in handle_one_ule_extension() are declared with 255 elements (valid indices 0-254), but the index htype is derived from network-controlled data as (ule_sndu_type & 0x00FF), giving a range of 0-255. When htype equals 255, an out-of-bounds read occurs on the function pointer table, and the OOB value may be called as a function pointer. Add a bounds check on htype against the array size before either table is accessed. Out-of-range values now cause the SNDU to be discarded.
linuxCWE-125Electron is a framework for writing cross-platform desktop applications using JavaScript, HTML and CSS
Electron is a framework for writing cross-platform desktop applications using JavaScript, HTML and CSS. Prior to versions 38.8.6, 39.8.0, 40.7.0, and 41.0.0-beta.8, an undocumented commandLineSwitches webPreference allowed arbitrary switches to be appended to the renderer process command line. Apps that construct webPreferences by spreading untrusted configuration objects may inadvertently allow an attacker to inject switches that disable renderer sandboxing or web security controls. Apps are only affected if they construct webPreferences from external or untrusted input without an allowlist. Apps that use a fixed, hardcoded webPreferences object are not affected. This issue has been patched in versions 38.8.6, 39.8.0, 40.7.0, and 41.0.0-beta.8.
electronjsCWE-88CWE-912prompts.chat prior to commit 1464475, contains an identity confusion vulnerability due to inconsistent case-sensitive and case-insensitiv...
prompts.chat prior to commit 1464475, contains an identity confusion vulnerability due to inconsistent case-sensitive and case-insensitive handling of usernames across write and read paths, allowing attackers to create case-variant usernames that bypass uniqueness checks. Attackers can exploit non-deterministic username resolution to impersonate victim accounts, replace profile content on canonical URLs, and inject attacker-controlled metadata and content across the platform.
fkaCWE-178prompts.chat prior to commit 30a8f04 contains a server-side request forgery vulnerability in the Fal.ai media status polling feature that...
prompts.chat prior to commit 30a8f04 contains a server-side request forgery vulnerability in the Fal.ai media status polling feature that allows authenticated users to perform arbitrary outbound requests by supplying attacker-controlled URLs in the token parameter. Attackers can exploit the lack of URL validation to disclose the FAL_API_KEY in the Authorization header, enabling credential theft, internal network probing, and abuse of the victim's Fal.ai account.
fkaCWE-918prompts.chat prior to commit 0f8d4c3 contains a path traversal vulnerability in skill file handling that allows attackers to write arbitr...
prompts.chat prior to commit 0f8d4c3 contains a path traversal vulnerability in skill file handling that allows attackers to write arbitrary files to the client system by crafting malicious ZIP archives with unsanitized filenames containing path traversal sequences. Attackers can exploit missing server-side filename validation to inject path traversal sequences ../ into skill file archives, which when extracted by vulnerable tools writing files outside the intended directory and overwriting shell initialization files to achieve code execution.
fkaCWE-22The Stackfield Desktop App before 1.10.2 for macOS and Windows contains a path traversal vulnerability in certain decryption functionalit...
The Stackfield Desktop App before 1.10.2 for macOS and Windows contains a path traversal vulnerability in certain decryption functionality when processing the filePath property. A malicious export can write arbitrary content to any path on the victim's filesystem.
stackfieldCWE-22In the Linux kernel, the following vulnerability has been resolved: NFSD: Defer sub-object cleanup in export put callbacks svc_export_p...
In the Linux kernel, the following vulnerability has been resolved: NFSD: Defer sub-object cleanup in export put callbacks svc_export_put() calls path_put() and auth_domain_put() immediately when the last reference drops, before the RCU grace period. RCU readers in e_show() and c_show() access both ex_path (via seq_path/d_path) and ex_client->name (via seq_escape) without holding a reference. If cache_clean removes the entry and drops the last reference concurrently, the sub-objects are freed while still in use, producing a NULL pointer dereference in d_path. Commit 2530766492ec ("nfsd: fix UAF when access ex_uuid or ex_stats") moved kfree of ex_uuid and ex_stats into the call_rcu callback, but left path_put() and auth_domain_put() running before the grace period because both may sleep and call_rcu callbacks execute in softirq context. Replace call_rcu/kfree_rcu with queue_rcu_work(), which defers the callback until after the RCU grace period and executes it in process context where sleeping is permitted. This allows path_put() and auth_domain_put() to be moved into the deferred callback alongside the other resource releases. Apply the same fix to expkey_put(), which has the identical pattern with ek_path and ek_client. A dedicated workqueue scopes the shutdown drain to only NFSD export release work items; flushing the shared system_unbound_wq would stall on unrelated work from other subsystems. nfsd_export_shutdown() uses rcu_barrier() followed by flush_workqueue() to ensure all deferred release callbacks complete before the export caches are destroyed. Reviwed-by: Jeff Layton <jlayton@kernel.org>
linuxCWE-476In the Linux kernel, the following vulnerability has been resolved: NFSD: Hold net reference for the lifetime of /proc/fs/nfs/exports fd...
In the Linux kernel, the following vulnerability has been resolved: NFSD: Hold net reference for the lifetime of /proc/fs/nfs/exports fd The /proc/fs/nfs/exports proc entry is created at module init and persists for the module's lifetime. exports_proc_open() captures the caller's current network namespace and stores its svc_export_cache in seq->private, but takes no reference on the namespace. If the namespace is subsequently torn down (e.g. container destruction after the opener does setns() to a different namespace), nfsd_net_exit() calls nfsd_export_shutdown() which frees the cache. Subsequent reads on the still-open fd dereference the freed cache_detail, walking a freed hash table. Hold a reference on the struct net for the lifetime of the open file descriptor. This prevents nfsd_net_exit() from running -- and thus prevents nfsd_export_shutdown() from freeing the cache -- while any exports fd is open. cache_detail already stores its net pointer (cd->net, set by cache_create_net()), so exports_release() can retrieve it without additional per-file storage.
linuxIn the Linux kernel, the following vulnerability has been resolved: nfsd: fix heap overflow in NFSv4.0 LOCK replay cache The NFSv4.0 re...
In the Linux kernel, the following vulnerability has been resolved: nfsd: fix heap overflow in NFSv4.0 LOCK replay cache The NFSv4.0 replay cache uses a fixed 112-byte inline buffer (rp_ibuf[NFSD4_REPLAY_ISIZE]) to store encoded operation responses. This size was calculated based on OPEN responses and does not account for LOCK denied responses, which include the conflicting lock owner as a variable-length field up to 1024 bytes (NFS4_OPAQUE_LIMIT). When a LOCK operation is denied due to a conflict with an existing lock that has a large owner, nfsd4_encode_operation() copies the full encoded response into the undersized replay buffer via read_bytes_from_xdr_buf() with no bounds check. This results in a slab-out-of-bounds write of up to 944 bytes past the end of the buffer, corrupting adjacent heap memory. This can be triggered remotely by an unauthenticated attacker with two cooperating NFSv4.0 clients: one sets a lock with a large owner string, then the other requests a conflicting lock to provoke the denial. We could fix this by increasing NFSD4_REPLAY_ISIZE to allow for a full opaque, but that would increase the size of every stateowner, when most lockowners are not that large. Instead, fix this by checking the encoded response length against NFSD4_REPLAY_ISIZE before copying into the replay buffer. If the response is too large, set rp_buflen to 0 to skip caching the replay payload. The status is still cached, and the client already received the correct response on the original request.
linuxCWE-787
8.8 HIGH
9.8 CRITICALWeekly digest
Get the curated CVE digest every Monday
One email a week, sent Monday morning CET. The CVEs published or modified in the last seven days, severity-ordered, with the QSearch coverage signal. Unsubscribe with one click — included in every send.
Pipe the CVE feed into your stack.
CVE Watch publishes RSS, Atom, and JSON feeds — wire them into your SIEM, Slack, Discord, or your RSS reader of choice. Or get the curated weekly digest by email.