aisecwatch.com
DashboardVulnerabilitiesNewsResearchArchiveStatsDataset
aisecwatch.com

Real-time AI security monitoring. Tracking AI-related vulnerabilities, safety and security incidents, privacy risks, research developments, and policy changes.

Navigation

VulnerabilitiesNewsResearchDigest ArchiveNewsletter ArchiveSubscribeData SourcesStatisticsDatasetAPIIntegrationsWidgetRSS Feed

Maintained by

Truong (Jack) Luu

Information Systems Researcher

AI & LLM Vulnerabilities

Security vulnerabilities, privacy incidents, safety concerns, and policy updates affecting LLMs and AI agents.

to
Export CSV
1465 items

CVE-2025-3730: A vulnerability, which was classified as problematic, was found in PyTorch 2.6.0. Affected is the function torch.nn.func

lowvulnerability
security
Apr 16, 2025
CVE-2025-3730

PyTorch 2.6.0 contains a vulnerability in the torch.nn.functional.ctc_loss function (a component used for speech recognition tasks) that can cause denial of service (making the system unavailable). The vulnerability requires local access to exploit and has been publicly disclosed, though its actual existence is still uncertain.

Fix: Apply patch 46fc5d8e360127361211cb237d5f9eef0223e567. The project's security policy also recommends avoiding unknown models, which could have malicious effects.

NVD/CVE Database

CVE-2025-3677: A vulnerability classified as critical was found in lm-sys fastchat up to 0.2.36. This vulnerability affects the functio

mediumvulnerability
security
Apr 16, 2025
CVE-2025-3677

A critical vulnerability (CVE-2025-3677) was found in lm-sys FastChat version 0.2.36 and earlier in the file apply_delta.py. The flaw involves deserialization (converting data back into code or objects, which can be dangerous if the data comes from an untrusted source) and can only be exploited by someone with local access to the affected system.

CVE-2025-31363: Mattermost versions 10.4.x <= 10.4.2, 10.5.x <= 10.5.0, 9.11.x <= 9.11.9 fail to restrict domains the LLM can request to

lowvulnerability
security
Apr 16, 2025
CVE-2025-31363

Mattermost (a team communication platform) versions 10.4.2 and earlier, 10.5.0 and earlier, and 9.11.9 and earlier don't properly block which websites their built-in AI tool can contact. This allows logged-in users to use prompt injection (tricking the AI by hiding instructions in their input) to steal data from servers that the Mattermost system can access.

CVE-2025-3579: In versions prior to Aidex 1.7, an authenticated malicious user, taking advantage of an open registry, could execute una

highvulnerability
security
Apr 15, 2025
CVE-2025-3579

In Aidex versions before 1.7, a logged-in attacker could exploit an open registry to run unauthorized commands on the system through prompt injection attacks (tricking the AI by hiding malicious instructions in user input) via the chat message endpoint. This allowed them to execute operating system commands, access databases, and invoke framework functions.

CVE-2025-32383: MaxKB (Max Knowledge Base) is an open source knowledge base question-answering system based on a large language model an

mediumvulnerability
security
Apr 10, 2025
CVE-2025-32383

MaxKB (Max Knowledge Base) is an open source system that answers questions using a large language model and RAG (retrieval-augmented generation, where an AI pulls in external documents to answer questions). A reverse shell vulnerability (a security flaw that lets attackers gain control of a system remotely) exists in its function library module and can be exploited by privileged users to create unauthorized access.

CVE-2025-32375: BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Prior to 1.4.

criticalvulnerability
security
Apr 9, 2025
CVE-2025-32375EPSS: 67.3%

BentoML is a Python library for building AI model serving systems, but versions before 1.4.8 had a vulnerability in its runner server that allowed attackers to execute arbitrary code (unauthorized commands) by sending specially crafted requests with specific headers and parameters, potentially giving them full access to the server and its data.

CVE-2025-26644: Automated recognition mechanism with inadequate detection or handling of adversarial input perturbations in Windows Hell

mediumvulnerability
security
Apr 8, 2025
CVE-2025-26644

CVE-2025-26644 is a vulnerability in Windows Hello (a biometric authentication system) where its recognition mechanism fails to properly detect or handle adversarial input perturbations (slight changes designed to fool AI systems). This weakness allows a local attacker to spoof someone's identity without authorization.

CVE-2025-32018: Cursor is a code editor built for programming with AI. In versions 0.45.0 through 0.48.6, the Cursor app introduced a re

highvulnerability
security
Apr 8, 2025
CVE-2025-32018

Cursor (a code editor designed for AI-assisted programming) had a bug in versions 0.45.0 through 0.48.6 where the Cursor Agent (an AI component that can automatically modify files) could be tricked into writing to files outside the workspace the user opened, either through direct user requests or hidden instructions in context. However, the risk was low because exploitation required deliberate prompting and any changes were visible to the user for review.

CVE-2025-3248: Langflow versions prior to 1.3.0 are susceptible to code injection in the /api/v1/validate/code endpoint. A remote and

criticalvulnerability
security
Apr 7, 2025
CVE-2025-3248EPSS: 92.1%🔥 Actively Exploited

CVE-2025-27520: BentoML is a Python library for building online serving systems optimized for AI apps and model inference. A Remote Code

criticalvulnerability
security
Apr 4, 2025
CVE-2025-27520EPSS: 81.0%

BentoML v1.4.2 contains a Remote Code Execution (RCE) vulnerability caused by insecure deserialization (unsafe handling of data conversion from storage format back into code objects), which allows unauthenticated users to execute arbitrary code on the server through an unsafe code segment in serde.py. This is a critical security flaw in a Python library used for building AI model serving systems.

CVE-2025-3136: A vulnerability, which was classified as problematic, has been found in PyTorch 2.6.0. This issue affects the function t

lowvulnerability
security
Apr 3, 2025
CVE-2025-3136

CVE-2025-3136 is a memory corruption vulnerability found in PyTorch 2.6.0, specifically in a function that manages GPU memory allocation. The vulnerability requires local access to exploit and has been publicly disclosed, though it is rated as medium severity with a CVSS score (a 0-10 rating of how severe a vulnerability is) of 4.8.

CVE-2025-3121: A vulnerability classified as problematic has been found in PyTorch 2.6.0. Affected is the function torch.jit.jit_module

lowvulnerability
security
Apr 2, 2025
CVE-2025-3121

CVE-2025-3121 is a memory corruption vulnerability (where a program accidentally writes data to wrong memory locations) found in PyTorch 2.6.0, specifically in the torch.jit.jit_module_from_flatbuffer function. An attacker with local access (meaning they can run code on the same computer) could exploit this vulnerability, and the exploit details have been publicly disclosed.

CVE-2025-31564: Improper Neutralization of Special Elements used in an SQL Command ('SQL Injection') vulnerability in aitool Ai Auto Too

highvulnerability
security
Apr 1, 2025
CVE-2025-31564

CVE-2025-31564 is a SQL injection vulnerability (a type of attack where an attacker inserts malicious database commands into user input) found in the Ai Auto Tool Content Writing Assistant WordPress plugin, versions up to 2.1.7. The vulnerability allows blind SQL injection (SQL attacks where the attacker cannot see direct results but can infer information through application behavior), potentially letting attackers access or manipulate the database.

CVE-2025-31843: Missing Authorization vulnerability in Wilson OpenAI Tools for WordPress & WooCommerce allows Exploiting Incorrectly Con

mediumvulnerability
security
Apr 1, 2025
CVE-2025-31843

CVE-2025-31843 is a missing authorization vulnerability (a security flaw where the software fails to properly check if a user has permission to perform an action) in the Wilson OpenAI Tools plugin for WordPress and WooCommerce that affects versions up to 2.1.5. The vulnerability allows attackers to exploit incorrectly configured access controls, meaning they can perform actions they shouldn't be allowed to do.

CVE-2025-3001: A vulnerability classified as critical was found in PyTorch 2.6.0. This vulnerability affects the function torch.lstm_ce

mediumvulnerability
security
Mar 31, 2025
CVE-2025-3001

PyTorch 2.6.0 contains a critical vulnerability (CVE-2025-3001) in the torch.lstm_cell function that causes memory corruption (damage to data stored in a computer's memory) through local manipulation. The vulnerability requires local access to exploit and has been publicly disclosed.

CVE-2025-3000: A vulnerability classified as critical has been found in PyTorch 2.6.0. This affects the function torch.jit.script. The

mediumvulnerability
security
Mar 31, 2025
CVE-2025-3000

A critical vulnerability (CVE-2025-3000) was found in PyTorch 2.6.0 affecting the torch.jit.script function, which causes memory corruption (damage to data stored in a computer's RAM). The vulnerability can be exploited locally (by someone with access to the same machine) and has already been publicly disclosed, making it a known risk.

CVE-2025-2999: A vulnerability was found in PyTorch 2.6.0. It has been rated as critical. Affected by this issue is the function torch.

mediumvulnerability
security
Mar 31, 2025
CVE-2025-2999

CVE-2025-2999 is a critical vulnerability in PyTorch 2.6.0 affecting the torch.nn.utils.rnn.unpack_sequence function, which causes memory corruption (unsafe access to computer memory). An attacker must have local access (ability to run code on the same machine) to exploit this bug, and the vulnerability has already been made public.

CVE-2025-2998: A vulnerability was found in PyTorch 2.6.0. It has been declared as critical. Affected by this vulnerability is the func

mediumvulnerability
security
Mar 31, 2025
CVE-2025-2998

PyTorch 2.6.0 contains a critical vulnerability (CVE-2025-2998) in the torch.nn.utils.rnn.pad_packed_sequence function that causes memory corruption (a situation where data in a program's memory is accidentally overwritten or damaged). An attacker with local access (ability to run code on the same machine) can exploit this flaw, and the vulnerability details have been publicly disclosed.

CVE-2025-2953: A vulnerability, which was classified as problematic, has been found in PyTorch 2.6.0+cu124. Affected by this issue is t

lowvulnerability
security
Mar 30, 2025
CVE-2025-2953

A vulnerability in PyTorch 2.6.0+cu124 affects the torch.mkldnn_max_pool2d function, a component used for processing image data. The vulnerability can cause a denial of service (making a system unavailable), but requires local access to the machine. The vulnerability's real existence is still disputed.

CVE-2025-30358: Mesop is a Python-based UI framework that allows users to build web applications. A class pollution vulnerability in Mes

highvulnerability
security
Mar 27, 2025
CVE-2025-30358

Mesop is a Python-based UI framework for building web applications that has a class pollution vulnerability (a flaw allowing attackers to modify global variables and class attributes at runtime, similar to prototype pollution in JavaScript) in versions before 0.14.1. This vulnerability could cause denial of service attacks (making a service unavailable), identity confusion where attackers impersonate system roles, jailbreak attacks against LLMs (large language models, AI systems that generate text), or potentially remote code execution (running unauthorized commands on a server) depending on how the application is built.

Previous32 / 74Next
NVD/CVE Database
NVD/CVE Database

Fix: Update to Aidex version 1.7 or later.

NVD/CVE Database

Fix: This vulnerability is fixed in v1.10.4-lts. Users should update to this version or later.

NVD/CVE Database

Fix: Update BentoML to version 1.4.8 or later, where this vulnerability is fixed.

NVD/CVE Database
NVD/CVE Database

Fix: This vulnerability is fixed in version 0.48.7.

NVD/CVE Database

Langflow versions before 1.3.0 have a code injection vulnerability (a flaw where attackers can insert and run malicious code) in the /api/v1/validate/code endpoint that allows unauthenticated attackers (those without login credentials) to execute arbitrary code by sending specially crafted HTTP requests (formatted messages to the server). This vulnerability is actively being exploited in the wild.

Fix: Update Langflow to version 1.3.0 or later, as referenced in the official release notes at https://github.com/langflow-ai/langflow/releases/tag/1.3.0. If mitigations are unavailable, discontinue use of the product.

NVD/CVE Database

Fix: This vulnerability is fixed in BentoML version 1.4.3. Users should upgrade from v1.4.2 to v1.4.3 or later.

NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database

Fix: Users should upgrade to version 0.14.1 to obtain a fix for the issue.

NVD/CVE Database