vllm-project vllm version v0.6.2 contains a vulnerability in the MessageQueue.dequeue() API function. The function uses pickle.loads to parse received sockets directly, leading to a remote code execution vulnerability. An attacker can exploit this by sending a malicious payload to the MessageQueue, causing the victim's machine to execute arbitrary code.

vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4 that ONLY impacts environments using the `PyNcclPipe` KV cache transfer integration with the V0 engine. No other configurations are affected. vLLM supports the use of the `PyNcclPipe` class to establish a peer-to-peer communication domain for data transmission between distributed nodes. The GPU-side KV-Cache transmission is implemented through the `PyNcclCommunicator` class, while CPU-side control message passing is handled via the `send_obj` and `recv_obj` methods on the CPU side.​ The intention was that this interface should only be exposed to a private network using the IP address specified by the `--kv-ip` CLI parameter. The vLLM documentation covers how this must be limited to a secured network. The default and intentional behavior from PyTorch is that the `TCPStore` interface listens on ALL interfaces, regardless of what IP address is provided. The IP address given was only used as a client-side address to use. vLLM was fixed to use a workaround to force the `TCPStore` instance to bind its socket to a specified private interface. As of version 0.8.5, vLLM limits the `TCPStore` socket to the private interface as configured.

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.6.5 and prior to 0.8.5, having vLLM integration with mooncake, are vulnerable to remote code execution due to using pickle based serialization over unsecured ZeroMQ sockets. The vulnerable sockets were set to listen on all network interfaces, increasing the likelihood that an attacker is able to reach the vulnerable ZeroMQ sockets to carry out an attack. vLLM instances that do not make use of the mooncake integration are not vulnerable. This issue has been patched in version 0.8.5.

vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a heap address. With this leak, we reduce ASLR from 4 billion guesses to ~8 guesses. This vulnerability can be chained a heap overflow with JPEG2000 decoder in OpenCV/FFmpeg to achieve remote code execution. This vulnerability is fixed in 0.14.1.

vLLM is an inference and serving engine for large language models (LLMs). The SSRF protection fix for CVE-2026-24779 add in 0.15.1 can be bypassed in the load_from_url_async method due to inconsistent URL parsing behavior between the validation layer and the actual HTTP client. The SSRF fix uses urllib3.util.parse_url() to validate and extract the hostname from user-provided URLs. However, load_from_url_async uses aiohttp for making the actual HTTP requests, and aiohttp internally uses the yarl library for URL parsing. This vulnerability in 0.17.0.

vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules during model resolution without gating on `trust_remote_code`, allowing attacker-controlled Python code in a model repo/path to execute at server startup. An attacker who can influence the model repo/path (local directory or remote Hugging Face repo) can achieve arbitrary code execution on the vLLM host during model load. This happens before any request handling and does not require API access. Version 0.14.0 fixes the issue.

vLLM is a library for LLM inference and serving. vllm/model_executor/weight_utils.py implements hf_model_weights_iterator to load the model checkpoint, which is downloaded from huggingface. It uses the torch.load function and the weights_only parameter defaults to False. When torch.load loads malicious pickle data, it will execute arbitrary code during unpickling. This vulnerability is fixed in v0.7.0.

vLLM is an inference and serving engine for large language models (LLMs). From versions 0.10.2 to before 0.11.1, a memory corruption vulnerability could lead to a crash (denial-of-service) and potentially remote code execution (RCE), exists in the Completions API endpoint. When processing user-supplied prompt embeddings, the endpoint loads serialized tensors using torch.load() without sufficient validation. Due to a change introduced in PyTorch 2.8.0, sparse tensor integrity checks are disabled by default. As a result, maliciously crafted tensors can bypass internal bounds checks and trigger an out-of-bounds memory write during the call to to_dense(). This memory corruption can crash vLLM and potentially lead to code execution on the server hosting vLLM. This issue has been patched in version 0.11.1.

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP on all network interfaces will allow attackers to execute remote code on distributed hosts. This is a remote code execution vulnerability impacting any deployments using Mooncake to distribute KV across distributed hosts. This vulnerability is fixed in 0.8.0.

vLLM is an inference and serving engine for large language models. In a multi-node vLLM deployment using the V0 engine, vLLM uses ZeroMQ for some multi-node communication purposes. The secondary vLLM hosts open a `SUB` ZeroMQ socket and connect to an `XPUB` socket on the primary vLLM host. When data is received on this `SUB` socket, it is deserialized with `pickle`. This is unsafe, as it can be abused to execute code on a remote machine. Since the vulnerability exists in a client that connects to the primary vLLM host, this vulnerability serves as an escalation point. If the primary vLLM host is compromised, this vulnerability could be used to compromise the rest of the hosts in the vLLM deployment. Attackers could also use other means to exploit the vulnerability without requiring access to the primary vLLM host. One example would be the use of ARP cache poisoning to redirect traffic to a malicious endpoint used to deliver a payload with arbitrary code to execute on the target machine. Note that this issue only affects the V0 engine, which has been off by default since v0.8.0. Further, the issue only applies to a deployment using tensor parallelism across multiple hosts, which we do not expect to be a common deployment pattern. Since V0 is has been off by default since v0.8.0 and the fix is fairly invasive, the maintainers of vLLM have decided not to fix this issue. Instead, the maintainers recommend that users ensure their environment is on a secure network in case this pattern is in use. The V1 engine is not affected by this issue.

VisiCut 2.1 allows code execution via Insecure XML Deserialization in the loadPlfFile method of VisicutModel.java.

Netwrix Password Secure 9.2.0.32454 allows OS command injection.

ObjectSocketWrapper.java in Gradle 2.12 allows remote attackers to execute arbitrary code via a crafted serialized object.

WeGIA is an open source Web Manager for Institutions with a focus on Portuguese language users. An OS Command Injection vulnerability was discovered in the WeGIA application, `gerenciar_backup.php` endpoint. This vulnerability could allow an attacker to execute arbitrary code remotely. This issue has been addressed in version 3.2.14 and all users are advised to upgrade. There are no known workarounds for this vulnerability.

An improper neutralization of special elements used in an OS command ('OS Command Injection') vulnerability [CWE-78] in Fortinet FortiSIEM version 7.3.0 through 7.3.1, 7.2.0 through 7.2.5, 7.1.0 through 7.1.7, 7.0.0 through 7.0.3 and before 6.7.9 allows an unauthenticated attacker to execute unauthorized code or commands via crafted CLI requests.

TOTOLINK A3002R V4.0.0-B20230531.1404 is vulnerable to Command Injection in /bin/boa via bandstr.

Deserialization of Untrusted Data vulnerability in ThemeREX Sound | Musical Instruments Online Store musicplace allows Object Injection.This issue affects Sound | Musical Instruments Online Store: from n/a through <= 1.6.9.

Several OS command injection vulnerabilities exist in the m2m binary of Siretta QUARTZ-GOLD G5.0.1.5-210720-141020. A specially-crafted network request can lead to arbitrary command execution. An attacker can send a network request to trigger these vulnerabilities.This command injection is reachable through the m2m's DOWNLOAD_CFG_FILE command

Deserialization of Untrusted Data vulnerability in Jthemes Prestige prestige allows Object Injection.This issue affects Prestige: from n/a through < 1.4.1.

Deserialization of Untrusted Data vulnerability in ThemeREX Extreme Store extremestore allows Object Injection.This issue affects Extreme Store: from n/a through <= 1.5.10.

In ScadaBR version 1.2.0, an OS Command Injection vulnerability could allow an attacker to execute commands as root on the SCADA system.

An issue was discovered in URVE Build 24.03.2020. By using the _internal/pc/vpro.php?mac=0&ip=0&operation=0&usr=0&pass=0%3bpowershell+-c+" substring, it is possible to execute a Powershell command and redirect its output to a file under the web root.

processCommandUpgrade() in libcommon.so in Petwant PF-103 firmware 4.22.2.42 and Petalk AI 3.2.2.30 allows remote attackers to execute arbitrary system commands as the root user.

Contao CMS through 3.2.4 has PHP Object Injection Vulnerabilities

Deserialization of Untrusted Data vulnerability in MetaSlider Responsive Slider by MetaSlider ml-slider allows Object Injection.This issue affects Responsive Slider by MetaSlider: from n/a through <= 3.94.0.

A vulnerability has been identified in OZW672 (All versions < V8.0), OZW772 (All versions < V8.0). The web service in affected devices does not sanitize the input parameters required for the `exportDiagramPage` endpoint. This could allow an unauthenticated remote attacker to execute arbitrary code with root privileges.

SolarWinds Web Help Desk was found to be susceptible to an unauthenticated AjaxProxy deserialization remote code execution vulnerability that, if exploited, would allow an attacker to run commands on the host machine. This vulnerability is a patch bypass of CVE-2024-28988, which in turn is a patch bypass of CVE-2024-28986.

An issue was discovered in Jamf Pro 9.x and 10.x before 10.15.1. Deserialization of untrusted data when parsing JSON in several APIs may cause Denial of Service (DoS), remote code execution (RCE), and/or deletion of files on the Jamf Pro server.

Yachtcontrol through 2019-10-06: It's possible to perform direct Operating System commands as an unauthenticated user via the "/pages/systemcall.php?command={COMMAND}" page and parameter, where {COMMAND} will be executed and returning the results to the client. Affects Yachtcontrol webservers disclosed via Dutch GPRS/4G mobile IP-ranges. IP addresses vary due to DHCP client leasing of telco's.

A vulnerability was found in Totolink A8000RU 7.1cu.643_b20200521. This vulnerability affects the function setDiagnosisCfg of the file /cgi-bin/cstecgi.cgi of the component Web Management Interface. The manipulation of the argument ip results in os command injection. The attack can be executed remotely. The exploit has been made public and could be used.

A vulnerability was determined in Totolink A8000RU 7.1cu.643_b20200521. This issue affects the function setTracerouteCfg of the file /cgi-bin/cstecgi.cgi of the component Web Management Interface. This manipulation of the argument command causes os command injection. The attack is possible to be carried out remotely. The exploit has been publicly disclosed and may be utilized.

A vulnerability was identified in Totolink A8000RU 7.1cu.643_b20200521. Impacted is the function setLanguageCfg of the file /cgi-bin/cstecgi.cgi of the component Web Management Interface. Such manipulation of the argument lang leads to os command injection. The attack may be performed from remote. The exploit is publicly available and might be used.

A security flaw has been discovered in Totolink A8000RU 7.1cu.643_b20200521. The affected element is the function setUpgradeFW of the file /cgi-bin/cstecgi.cgi of the component Web Management Interface. Performing a manipulation of the argument resetFlags results in os command injection. It is possible to initiate the attack remotely. The exploit has been released to the public and may be used for attacks.

A weakness has been identified in Totolink A8000RU 7.1cu.643_b20200521. The impacted element is the function setScheduleCfg of the file /cgi-bin/cstecgi.cgi of the component Web Management Interface. Executing a manipulation of the argument mode can lead to os command injection. It is possible to launch the attack remotely. The exploit has been made available to the public and could be used for attacks.

Orkes Conductor v3.21.11 allows remote attackers to execute arbitrary OS commands through unrestricted access to Java classes.

A vulnerability was identified in Totolink A8000RU 7.1cu.643_b20200521. This affects the function setDdnsCfg of the file /cgi-bin/cstecgi.cgi of the component Web Management Interface. Such manipulation of the argument provider leads to os command injection. The attack may be launched remotely. The exploit is publicly available and might be used.

A security flaw has been discovered in Totolink A8000RU 7.1cu.643_b20200521. This impacts the function setGameSpeedCfg of the file /cgi-bin/cstecgi.cgi of the component Web Management Interface. Performing a manipulation of the argument enable results in os command injection. Remote exploitation of the attack is possible. The exploit has been released to the public and may be used for attacks.

A weakness has been identified in Totolink A8000RU 7.1cu.643_b20200521. Affected is the function setRemoteCfg of the file /cgi-bin/cstecgi.cgi of the component Web Management Interface. Executing a manipulation of the argument enable can lead to os command injection. The attack can be executed remotely. The exploit has been made available to the public and could be used for attacks.

A security vulnerability has been detected in Totolink A8000RU 7.1cu.643_b20200521. Affected by this vulnerability is the function setFirewallType of the file /cgi-bin/cstecgi.cgi of the component Web Management Interface. The manipulation of the argument firewallType leads to os command injection. The attack is possible to be carried out remotely. The exploit has been disclosed publicly and may be used.

A vulnerability was detected in Totolink A8000RU 7.1cu.643_b20200521. Affected by this issue is the function setStaticDhcpRules of the file /cgi-bin/cstecgi.cgi of the component Web Management Interface. The manipulation of the argument enable results in os command injection. The attack may be performed from remote. The exploit is now public and may be used.

A command injection vulnerability exists in Jitsi before commit 8aa7be58522f4264078d54752aae5483bfd854b2 when launching browsers on Windows which could allow an attacker to insert an arbitrary URL which opens up the opportunity to remote execution.

A weakness has been identified in Totolink A8000RU 7.1cu.643_b20200521. This issue affects the function setMacFilterRules of the file /cgi-bin/cstecgi.cgi of the component Web Management Interface. This manipulation of the argument enable causes os command injection. The attack may be initiated remotely. The exploit has been made available to the public and could be used for attacks.

A security vulnerability has been detected in Totolink A8000RU 7.1cu.643_b20200521. Impacted is the function setWiFiWpsCfg of the file /cgi-bin/cstecgi.cgi of the component Web Management Interface. Such manipulation of the argument wscDisabled leads to os command injection. The attack may be launched remotely. The exploit has been disclosed publicly and may be used.

A vulnerability was detected in Totolink A8000RU 7.1cu.643_b20200521. The affected element is the function setQosCfg of the file /cgi-bin/cstecgi.cgi of the component Web Management Interface. Performing a manipulation of the argument enable results in os command injection. Remote exploitation of the attack is possible. The exploit is now public and may be used.

A flaw has been found in Totolink A8000RU 7.1cu.643_b20200521. The impacted element is the function setL2tpServerCfg of the file /cgi-bin/cstecgi.cgi of the component Web Management Interface. Executing a manipulation of the argument enable can lead to os command injection. The attack can be executed remotely. The exploit has been published and may be used.

ColdFusion versions 2023.12, 2021.18, 2025.0 and earlier are affected by a Deserialization of Untrusted Data vulnerability that could result in arbitrary code execution in the context of the current user resulting in a High impact to Confidentiality and Integrity. Exploitation of this issue does not require user interaction.

A flaw has been found in Totolink A8000RU 7.1cu.643_b20200521. This vulnerability affects the function setOpenVpnCertGenerationCfg of the file /cgi-bin/cstecgi.cgi of the component Web Management Interface. Executing a manipulation of the argument servername can lead to os command injection. The attack may be launched remotely. The exploit has been published and may be used.

A vulnerability has been found in Totolink A8000RU 7.1cu.643_b20200521. This issue affects the function UploadOpenVpnCert of the file /cgi-bin/cstecgi.cgi of the component Web Management Interface. The manipulation of the argument FileName leads to os command injection. Remote exploitation of the attack is possible. The exploit has been disclosed to the public and may be used.

A vulnerability was found in Totolink A8000RU 7.1cu.643_b20200521. Impacted is the function setOpenVpnCfg of the file /cgi-bin/cstecgi.cgi of the component Web Management Interface. The manipulation of the argument enabled results in os command injection. The attack can be executed remotely. The exploit has been made public and could be used.

A vulnerability was determined in Totolink A8000RU 7.1cu.643_b20200521. The affected element is the function UploadFirmwareFile of the file /cgi-bin/cstecgi.cgi of the component Web Management Interface. This manipulation of the argument FileName causes os command injection. The attack is possible to be carried out remotely. The exploit has been publicly disclosed and may be utilized.