Changelog

This week’s release introduces a new detection signature that enhances coverage for a critical vulnerability in Windows Server Update Services (WSUS), tracked as CVE-2025-59287.

Key Findings

The vulnerability allows unauthenticated attackers to potentially achieve remote code execution. The updated detection logic strengthens defenses by improving resilience against exploitation attempts targeting this flaw.

Impact

Successful exploitation of CVE-2025-59287 could enable attackers to hijack sessions, execute arbitrary commands, exfiltrate sensitive data, and disrupt storefront operations. These actions pose significant confidentiality and integrity risks to affected environments. Administrators should apply vendor patches immediately to mitigate exposure.

This week highlights enhancements to detection signatures improving coverage for vulnerabilities in Adobe Commerce and Magento Open Source, linked to CVE-2025-54236.

Key Findings

This vulnerability allows unauthenticated attackers to take over customer accounts through the Commerce REST API and, in certain configurations, may lead to remote code execution. The latest update enhances detection logic to provide more resilient protection against exploitation attempts.

Impact

Adobe Commerce (CVE-2025-54236): Exploitation may allow attackers to hijack sessions, execute arbitrary commands, steal data, and disrupt storefronts, resulting in confidentiality and integrity risks for merchants. Administrators are strongly encouraged to apply vendor patches without delay.

This week’s update introduces an enhanced rule that expands detection coverage for a critical vulnerability in Oracle E-Business Suite. It also improves an existing rule to provide more reliable coverage in request processing.

Key Findings

New WAF rule deployed for Oracle E-Business Suite (CVE-2025-61882) to block unauthenticated attacker's network access via HTTP to compromise Oracle Concurrent Processing. If successfully exploited, this vulnerability may result in remote code execution.

Impact

• Successful exploitation of CVE-2025-61882 allows unauthenticated attackers to execute arbitrary code remotely by chaining multiple weaknesses, enabling lateral movement into internal services, data exfiltration, and large-scale extortionware deployment within Oracle E-Business Suite environments.

Cloudflare's new Application Security report, currently in Closed Beta, is now available in the dashboard.

The reports are generated monthly and provide cyber security insights trends for all of the Enterprise zones in your Cloudflare account.

The reports also include an industry benchmark, comparing your cyber security landscape to peers in your industry.

Learn more about the reports by referring to the Security Reports documentation.

Use the feedback survey link at the top of the page to help us improve the reports.

This week we introduced several new detections across Cloudflare Managed Rulesets, expanding coverage for high-impact vulnerability classes such as SSRF, SQLi, SSTI, Reverse Shell attempts, and Prototype Pollution. These rules aim to improve protection against attacker-controlled payloads that exploit misconfigurations or unvalidated input in web applications.

Key Findings

New detections added for multiple exploit categories:

SSRF (Server-Side Request Forgery) — new rules targeting both local and cloud metadata abuse patterns (Beta).

SQL Injection (SQLi) — rules for common patterns, sleep/time-based injections, and string/wait function exploitation across headers and URIs.

SSTI (Server-Side Template Injection) — arithmetic-based probe detections introduced across URI, header, and body fields.

Reverse Shell and XXE payloads — enhanced heuristics for command execution and XML external entity misuse.

Prototype Pollution — new Beta rule identifying common JSON payload structures used in object prototype poisoning.

PHP Wrapper Injection and HTTP Parameter Pollution detections — to catch path traversal and multi-parameter manipulation attempts.

Anomaly Header Checks — detecting CRLF injection attempts in header names.

Impact

These updates help detect multi-vector payloads that blend SSRF + RCE or SQLi + SSTI attacks, especially in cloud-hosted applications with exposed metadata endpoints or unsafe template rendering.

Prototype Pollution and HTTP parameter pollution rules address emerging JavaScript supply-chain exploitation patterns increasingly seen in real-world incidents.

This week’s highlights include a new JinJava rule targeting a sandbox-bypass flaw that could allow malicious template input to escape execution controls. The rule improves detection for unsafe template rendering paths.

Key Findings

New WAF rule deployed for JinJava (CVE-2025-59340) to block a sandbox bypass in the template engine that permits attacker-controlled type construction and arbitrary class instantiation; in vulnerable environments this can escalate to remote code execution and full server compromise.

Impact

• CVE-2025-59340 — Exploitation enables attacker-supplied type descriptors / Jackson ObjectMapper abuse, allowing arbitrary class loading, file/URL access (LFI/SSRF primitives) and, with suitable gadget chains, potential remote code execution and system compromise.

This week highlights multiple critical Cisco vulnerabilities (CVE-2025-20363, CVE-2025-20333, CVE-2025-20362). This flaw stems from improper input validation in HTTP(S) requests. An authenticated VPN user could send crafted requests to execute code as root, potentially compromising the device. The initial two rules were made available on September 28, with a third rule added today, October 7, for more robust protection.

• Cisco (CVE-2025-20333, CVE-2025-20362, CVE-2025-20363): Multiple vulnerabilities that could allow attackers to exploit unsafe deserialization and input validation flaws. Successful exploitation may result in arbitrary code execution, privilege escalation, or command injection on affected systems.

Impact

Cisco (CVE-2025-20333, CVE-2025-20362, CVE-2025-20363): Exploitation enables attackers to escalate privileges or achieve remote code execution via command injection. Administrators are strongly advised to apply vendor updates immediately.

This week’s highlights prioritise an emergency Oracle E-Business Suite RCE rule deployed to block active, high-impact exploitation. Also addressed are high-severity Chaos Mesh controller command-injection flaws that enable unauthenticated in-cluster RCE and potential cluster compromise, plus a form-data multipart boundary issue that permits HTTP Parameter Pollution (HPP). Two new generic SQLi detections were added to catch inline-comment obfuscation and information disclosure techniques.

Key Findings

• New emergency rule released for Oracle E-Business Suite (CVE-2025-61882) addressing an actively exploited remote code execution vulnerability in core business application modules. Immediate mitigation deployed to protect enterprise workloads.

• Chaos Mesh (CVE-2025-59358,CVE-2025-59359,CVE-2025-59360,CVE-2025-59361): A GraphQL debug endpoint on the Chaos Controller Manager is exposed without authentication; several controller mutations (cleanTcs, killProcesses, cleanIptables) are vulnerable to OS command injection.

• Form-Data (CVE-2025-7783): Attackers who can observe Math.random() outputs and control request fields in form-data may exploit this flaw to perform HTTP parameter pollution, leading to request tampering or data manipulation.

• Two new generic SQLi detections added to enhance baseline coverage against inline-comment obfuscation and information disclosure attempts.

Impact

• CVE-2025-61882 — Oracle E-Business Suite remote code execution (emergency detection): attacker-controlled input can yield full system compromise, data exfiltration, and operational outage; immediate blocking enforced.

• CVE-2025-59358 / CVE-2025-59359 / CVE-2025-59360 / CVE-2025-59361 — Unauthenticated command-injection in Chaos Mesh controllers allowing remote code execution, cluster compromise, and service disruption (high availability risk).

• CVE-2025-7783 — Predictable multipart boundaries in form-data enabling HTTP Parameter Pollution; results include request tampering, parameter overwrite, and downstream data integrity loss.

Managed Ruleset Updated

This update introduces 21 new detections in the Cloudflare Managed Ruleset (all currently set to Disabled mode to preserve remediation logic and allow quick activation if needed). The rules cover a broad spectrum of threats - SQL injection techniques, command and code injection, information disclosure of common files, URL anomalies, and cross-site scripting.

This week highlights four important vendor- and component-specific issues: an authentication bypass in SimpleHelp (CVE-2024-57727), an information-disclosure flaw in Flowise Cloud (CVE-2025-58434), an SSRF in the WordPress plugin Ditty (CVE-2025-8085), and a directory-traversal bug in Vite (CVE-2025-30208). These are paired with improvements to our generic detection coverage (SQLi, SSRF) to raise the baseline and reduce noisy gaps.

Key Findings

• SimpleHelp (CVE-2024-57727): Authentication bypass in SimpleHelp that can allow unauthorized access to management interfaces or sessions.

• Flowise Cloud (CVE-2025-58434): Information-disclosure vulnerability in Flowise Cloud that may expose sensitive configuration or user data to unauthenticated or low-privileged actors.

• WordPress:Plugin: Ditty (CVE-2025-8085): SSRF in the Ditty WordPress plugin enabling server-side requests that could reach internal services or cloud metadata endpoints.

• Vite (CVE-2025-30208): Directory-traversal vulnerability in Vite allowing access to filesystem paths outside the intended web root.

Impact

These vulnerabilities allow attackers to gain access, escalate privileges, or execute actions that were previously unavailable:

• SimpleHelp (CVE-2024-57727): An authentication bypass that can let unauthenticated attackers access management interfaces or hijack sessions — enabling lateral movement, credential theft, or privilege escalation within affected environments.

• Flowise Cloud (CVE-2025-58434): Information-disclosure flaw that can expose sensitive configuration, tokens, or user data; leaked secrets may be chained into account takeover or privileged access to backend services.

• WordPress:Plugin: Ditty (CVE-2025-8085): SSRF that enables server-side requests to internal services or cloud metadata endpoints, potentially allowing attackers to retrieve credentials or reach otherwise inaccessible infrastructure, leading to privilege escalation or cloud resource compromise.

• Vite (CVE-2025-30208): Directory-traversal vulnerability that can expose filesystem contents outside the web root (configuration files, keys, source code), which attackers can use to escalate privileges or further compromise systems.

This week highlights multiple critical Cisco vulnerabilities (CVE-2025-20363, CVE-2025-20333, CVE-2025-20362). This flaw stems from improper input validation in HTTP(S) requests. An authenticated VPN user could send crafted requests to execute code as root, potentially compromising the device.

Key Findings

• Cisco (CVE-2025-20333, CVE-2025-20362, CVE-2025-20363): Multiple vulnerabilities that could allow attackers to exploit unsafe deserialization and input validation flaws. Successful exploitation may result in arbitrary code execution, privilege escalation, or command injection on affected systems.

Impact

Cisco (CVE-2025-20333, CVE-2025-20362, CVE-2025-20363): Exploitation enables attackers to escalate privileges or achieve remote code execution via command injection.

Managed Ruleset Updated

This update introduces 11 new detections in the Cloudflare Managed Ruleset (all currently set to Disabled mode to preserve remediation logic and allow quick activation if needed). The rules cover a broad spectrum of threats - SQL injection techniques, command and code injection, information disclosure of common files, URL anomalies, and cross-site scripting.

This week highlights a critical vendor-specific vulnerability: a deserialization flaw in the License Servlet of Fortra’s GoAnywhere MFT. By forging a license response signature, an attacker can trigger deserialization of arbitrary objects, potentially leading to command injection.

Key Findings

• GoAnywhere MFT (CVE-2025-10035): Deserialization vulnerability in the License Servlet that allows attackers with a forged license response signature to deserialize arbitrary objects, potentially resulting in command injection.

Impact

GoAnywhere MFT (CVE-2025-10035): Exploitation enables attackers to escalate privileges or achieve remote code execution via command injection.

This week emphasizes two critical vendor-specific vulnerabilities: a full elevation-of-privilege in Microsoft Azure Networking (CVE-2025-54914) and a server-side template injection (SSTI) leading to remote code execution (RCE) in Skyvern (CVE-2025-49619). These are complemented by enhancements in generic detections (SQLi, SSRF) to improve baseline coverage.

Key Findings

• Azure (CVE-2025-54914): Vulnerability in Azure Networking allowing elevation of privileges.

• Skyvern (CVE-2025-49619): Skyvern ≤ 0.1.85 has a server-side template injection (SSTI) vulnerability in its Prompt field (workflow blocks) via Jinja2. Authenticated users with low privileges can get remote code execution (blind).

• Generic SQLi / SSRF improvements: Expanded rule coverage to detect obfuscated SQL injection patterns and SSRF across host, local, and cloud contexts.

Impact

These vulnerabilities allow attackers to escalate privileges or execute code under conditions where previously they could not:

• Azure CVE-2025-54914 enables an attacker from the network with no credentials to gain high-level access within Azure Networking; could lead to full compromise of networking components.

• Skyvern CVE-2025-49619 allows authenticated users with minimal privilege to exploit SSTI for remote code execution, undermining isolation of workflow components.

• The improvements for SQLi and SSRF reduce risk from common injection and request-based attacks.

You can now route private traffic to Cloudflare Tunnel based on a hostname or domain, moving beyond the limitations of IP-based routing. This new capability is free for all Cloudflare One customers.

Previously, Tunnel routes could only be defined by IP address or CIDR range. This created a challenge for modern applications with dynamic or ephemeral IP addresses, often forcing administrators to maintain complex and brittle IP lists.

What’s new:

• Hostname & Domain Routing: Create routes for individual hostnames (e.g., payroll.acme.local) or entire domains (e.g., *.acme.local) and direct their traffic to a specific Tunnel.
• Simplified Zero Trust Policies: Build resilient policies in Cloudflare Access and Gateway using stable hostnames, making it dramatically easier to apply per-resource authorization for your private applications.
• Precise Egress Control: Route traffic for public hostnames (e.g., bank.example.com) through a specific Tunnel to enforce a dedicated source IP, solving the IP allowlist problem for third-party services.
• No More IP Lists: This feature makes the workaround of maintaining dynamic IP Lists for Tunnel connections obsolete.

Get started in the Tunnels section of the Zero Trust dashboard with your first private hostname or public hostname route.

Learn more in our blog post ↗.

This week's update

This week's focus highlights newly disclosed vulnerabilities in DevOps tooling, data visualization platforms, and enterprise CMS solutions. These issues include sensitive information disclosure and remote code execution, putting organizations at risk of credential leakage, unauthorized access, and full system compromise.

Key Findings

• Argo CD (CVE-2025-55190): Exposure of sensitive information could allow attackers to access credential data stored in configurations, potentially leading to compromise of Kubernetes workloads and secrets.

• DataEase (CVE-2025-57773): Insufficient input validation enables JNDI injection and insecure deserialization, resulting in remote code execution (RCE). Successful exploitation grants attackers control over the application server.

• Sitecore (CVE-2025-53694): A sensitive information disclosure flaw allows unauthorized access to confidential information stored in Sitecore deployments, raising the risk of data breaches and privilege escalation.

Impact

These vulnerabilities expose organizations to serious risks, including credential theft, unauthorized access, and full system compromise. Argo CD's flaw may expose Kubernetes secrets, DataEase exploitation could give attackers remote execution capabilities, and Sitecore's disclosure issue increases the likelihood of sensitive data leakage and business impact.

Administrators are strongly advised to apply vendor patches immediately, rotate exposed credentials, and review access controls to mitigate these risks.

This week's update

This week’s focus highlights newly disclosed vulnerabilities in web frameworks, enterprise applications, and widely deployed CMS plugins. The vulnerabilities include SSRF, authentication bypass, arbitrary file upload, and remote code execution (RCE), exposing organizations to high-impact risks such as unauthorized access, system compromise, and potential data exposure. In addition, security rule enhancements have been deployed to cover general command injection and server-side injection attacks, further strengthening protections.

Key Findings

• Next.js (CVE-2025-57822): Improper handling of redirects in custom middleware can lead to server-side request forgery (SSRF) when user-supplied headers are forwarded. Attackers could exploit this to access internal services or cloud metadata endpoints. The issue has been resolved in versions 14.2.32 and 15.4.7. Developers using custom middleware should upgrade and verify proper redirect handling in next() calls.

• ScriptCase (CVE-2025-47227, CVE-2025-47228): In the Production Environment extension in Netmake ScriptCase through 9.12.006 (23), two vulnerabilities allow attackers to reset admin accounts and execute system commands, potentially leading to full compromise of affected deployments.

• Sar2HTML (CVE-2025-34030): In Sar2HTML version 3.2.2 and earlier, insufficient input sanitization of the plot parameter allows remote, unauthenticated attackers to execute arbitrary system commands. Exploitation could compromise the underlying server and its data.

• Zhiyuan OA (CVE-2025-34040): An arbitrary file upload vulnerability exists in the Zhiyuan OA platform. Improper validation in the wpsAssistServlet interface allows unauthenticated attackers to upload crafted files via path traversal, which can be executed on the web server, leading to remote code execution.

• WordPress:Plugin:InfiniteWP Client (CVE-2020-8772): A vulnerability in the InfiniteWP Client plugin allows attackers to perform restricted actions and gain administrative control of connected WordPress sites.

Impact

These vulnerabilities could allow attackers to gain unauthorized access, execute malicious code, or take full control of affected systems. The Next.js SSRF flaw may expose internal services or cloud metadata endpoints to attackers. Exploitations of ScriptCase and Sar2HTML could result in remote code execution, administrative takeover, and full server compromise. In Zhiyuan OA, the arbitrary file upload vulnerability allows attackers to execute malicious code on the web server, potentially exposing sensitive data and applications. The authentication bypass in WordPress InfiniteWP Client enables attackers to gain administrative access, risking data exposure and unauthorized control of connected sites.

Administrators are strongly advised to apply vendor patches immediately, remove unsupported software, and review authentication and access controls to mitigate these risks.

This week's update

This week, new critical vulnerabilities were disclosed in Sitecore’s Sitecore Experience Manager (XM), Sitecore Experience Platform (XP), specifically versions 9.0 through 9.3, and 10.0 through 10.4. These flaws are caused by unsafe data deserialization and code reflection, leaving affected systems at high risk of exploitation.

Key Findings

• CVE-2025-53690: Remote Code Execution through Insecure Deserialization
• CVE-2025-53691: Remote Code Execution through Insecure Deserialization
• CVE-2025-53693: HTML Cache Poisoning through Unsafe Reflections

Impact

Exploitation could allow attackers to execute arbitrary code remotely on the affected system and conduct cache poisoning attacks, potentially leading to further compromise. Applying the latest vendor-released solution without delay is strongly recommended.

Starting December 1, 2025, list endpoints for the Cloudflare Tunnel API and Zero Trust Networks API will no longer return deleted tunnels, routes, subnets and virtual networks by default. This change makes the API behavior more intuitive by only returning active resources unless otherwise specified.

No action is required if you already explicitly set is_deleted=false or if you only need to list active resources.

This change affects the following API endpoints:

• List all tunnels: GET /accounts/{account_id}/tunnels
• List Cloudflare Tunnels: GET /accounts/{account_id}/cfd_tunnel
• List WARP Connector tunnels: GET /accounts/{account_id}/warp_connector
• List tunnel routes: GET /accounts/{account_id}/teamnet/routes
• List subnets: GET /accounts/{account_id}/zerotrust/subnets
• List virtual networks: GET /accounts/{account_id}/teamnet/virtual_networks

The default behavior of the is_deleted query parameter will be updated.

If you need to retrieve deleted (or all) resources, please update your API calls to explicitly include the is_deleted parameter before December 1, 2025.

To get a list of only deleted resources, you must now explicitly add the is_deleted=true query parameter to your request:

# Example: Get ONLY deleted Tunnels
curl "https://api.cloudflare.com/client/v4/accounts/$ACCOUNT_ID/tunnels?is_deleted=true" \
     -H "Authorization: Bearer $API_TOKEN"

# Example: Get ONLY deleted Virtual Networks
curl "https://api.cloudflare.com/client/v4/accounts/$ACCOUNT_ID/teamnet/virtual_networks?is_deleted=true" \
     -H "Authorization: Bearer $API_TOKEN"

Following this change, retrieving a complete list of both active and deleted resources will require two separate API calls: one to get active items (by omitting the parameter or using is_deleted=false) and one to get deleted items (is_deleted=true).

This update is based on user feedback and aims to:

• Create a more intuitive default: Aligning with common API design principles where list operations return only active resources by default.
• Reduce unexpected results: Prevents users from accidentally operating on deleted resources that were returned unexpectedly.
• Improve performance: For most users, the default query result will now be smaller and more relevant.

To learn more, please visit the Cloudflare Tunnel API and Zero Trust Networks API documentation.

This week's update

This week, a critical vulnerability was disclosed in Fortinet FortiWeb (versions 7.6.3 and below, versions 7.4.7 and below, versions 7.2.10 and below, and versions 7.0.10 and below), linked to improper parameter handling that could allow unauthorized access.

Key Findings

• Fortinet FortiWeb (CVE-2025-52970): A vulnerability may allow an unauthenticated remote attacker with access to non-public information to log in as any existing user on the device via a specially crafted request.

Impact

Exploitation could allow an unauthenticated attacker to impersonate any existing user on the device, potentially enabling them to modify system settings or exfiltrate sensitive information, posing a serious security risk. Upgrading to the latest vendor-released version is strongly recommended.

This week's update

This week, new critical vulnerabilities were disclosed in Next.js’s image optimization functionality, exposing a broad range of production environments to risks of data exposure and cache manipulation.

Key Findings

• CVE-2025-55173: Arbitrary file download from the server via image optimization.

• CVE-2025-57752: Cache poisoning leading to unauthorized data disclosure.

Impact

Exploitation could expose sensitive files, leak user or backend data, and undermine application trust. Given Next.js’s wide use, immediate patching and cache hardening are strongly advised.

Cloudflare Secrets Store is now integrated with AI Gateway, allowing you to store, manage, and deploy your AI provider keys in a secure and seamless configuration through Bring Your Own Key ↗. Instead of passing your AI provider keys directly in every request header, you can centrally manage each key with Secrets Store and deploy in your gateway configuration using only a reference, rather than passing the value in plain text.

You can now create a secret directly from your AI Gateway in the dashboard ↗ by navigating into your gateway -> Provider Keys -> Add.

You can also create your secret with the newly available ai_gateway scope via wrangler ↗, the Secrets Store dashboard ↗, or the API ↗.

Then, pass the key in the request header using its Secrets Store reference:

curl -X POST https://gateway.ai.cloudflare.com/v1/<ACCOUNT_ID>/my-gateway/anthropic/v1/messages \
 --header 'cf-aig-authorization: ANTHROPIC_KEY_1 \
 --header 'anthropic-version: 2023-06-01' \
 --header 'Content-Type: application/json' \
 --data  '{"model": "claude-3-opus-20240229", "messages": [{"role": "user", "content": "What is Cloudflare?"}]}'

Or, using Javascript:

import Anthropic from '@anthropic-ai/sdk';


const anthropic = new Anthropic({
 apiKey: "ANTHROPIC_KEY_1",
 baseURL: "https://gateway.ai.cloudflare.com/v1/<ACCOUNT_ID>/my-gateway/anthropic",
});


const message = await anthropic.messages.create({
 model: 'claude-3-opus-20240229',
 messages: [{role: "user", content: "What is Cloudflare?"}],
 max_tokens: 1024
});

For more information, check out the blog ↗!

This week's update

This week, critical vulnerabilities were disclosed that impact widely used open-source infrastructure, creating high-risk scenarios for code execution and operational disruption.

Key Findings

• Apache HTTP Server – Code Execution (CVE-2024-38474): A flaw in Apache HTTP Server allows attackers to achieve remote code execution, enabling full compromise of affected servers. This vulnerability threatens the confidentiality, integrity, and availability of critical web services.

• Laravel (CVE-2024-55661): A security flaw in Laravel introduces the potential for remote code execution under specific conditions. Exploitation could provide attackers with unauthorized access to application logic and sensitive backend data.

Impact

These vulnerabilities pose severe risks to enterprise environments and open-source ecosystems. Remote code execution enables attackers to gain deep system access, steal data, disrupt services, and establish persistent footholds for broader intrusions. Given the widespread deployment of Apache HTTP Server and Laravel in production systems, timely patching and mitigation are critical.

This week's update

This week, a series of critical vulnerabilities were discovered impacting core enterprise and open-source infrastructure. These flaws present a range of risks, providing attackers with distinct pathways for remote code execution, methods to breach internal network boundaries, and opportunities for critical data exposure and operational disruption.

Key Findings

• SonicWall SMA (CVE-2025-32819, CVE-2025-32820, CVE-2025-32821): A remote authenticated attacker with SSLVPN user privileges can bypass path traversal protections. These vulnerabilities enable a attacker to bypass security checks to read, modify, or delete arbitrary files. An attacker with administrative privileges can escalate this further, using a command injection flaw to upload malicious files, which could ultimately force the appliance to reboot to its factory default settings.

• Ms-Swift Project (CVE-2025-50460): An unsafe deserialization vulnerability exists in the Ms-Swift project's handling of YAML configuration files. If an attacker can control the content of a configuration file passed to the application, they can embed a malicious payload that will execute arbitrary code and it can be executed during deserialization.

• Apache Druid (CVE-2023-25194): This vulnerability in Apache Druid allows an attacker to cause the server to connect to a malicious LDAP server. By sending a specially crafted LDAP response, the attacker can trigger an unrestricted deserialization of untrusted data. If specific "gadgets" (classes that can be abused) are present in the server's classpath, this can be escalated to achieve Remote Code Execution (RCE).

• Tenda AC8v4 (CVE-2025-51087, CVE-2025-51088): Vulnerabilities allow an authenticated attacker to trigger a stack-based buffer overflow. By sending malformed arguments in a request to specific endpoints, an attacker can crash the device or potentially achieve arbitrary code execution.

• Open WebUI (CVE-2024-7959): This vulnerability allows a user to change the OpenAI URL endpoint to an arbitrary internal network address without proper validation. This flaw can be exploited to access internal services or cloud metadata endpoints, potentially leading to remote command execution if the attacker can retrieve instance secrets or access sensitive internal APIs.

• BentoML (CVE-2025-54381): The vulnerability exists in the serialization/deserialization handlers for multipart form data and JSON requests, which automatically download files from user-provided URLs without proper validation of internal network addresses. This allows attackers to fetch from unintended internal services, including cloud metadata and localhost.

• Adobe Experience Manager Forms (CVE-2025-54254): An Improper Restriction of XML External Entity Reference ('XXE') vulnerability that could lead to arbitrary file system read in Adobe AEM (≤6.5.23).

Impact

These vulnerabilities affect core infrastructure, from network security appliances like SonicWall to data platforms such as Apache Druid and ML frameworks like BentoML. The code execution and deserialization flaws are particularly severe, offering deep system access that allows attackers to steal data, disrupt services, and establish a foothold for broader intrusions. Simultaneously, SSRF and XXE vulnerabilities undermine network boundaries, exposing sensitive internal data and creating pathways for lateral movement. Beyond data-centric threats, flaws in edge devices like the Tenda router introduce the tangible risk of operational disruption, highlighting a multi-faceted threat to the security and stability of key enterprise systems.