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-2025-49131: FastGPT is an open-source project that provides a platform for building, deploying, and operating AI-driven workflows an

mediumvulnerability
security
Jun 9, 2025
CVE-2025-49131

FastGPT is an open-source platform for building AI workflows and chatbots that uses a sandbox (an isolated container designed to safely run untrusted code). Versions before 4.9.11 had weak isolation that allowed attackers to escape the sandbox by using overly permissive syscalls (system calls, which are requests programs make to the operating system), letting them read files, modify files, and bypass security restrictions. The vulnerability is fixed in version 4.9.11 by limiting which system calls are allowed to a safer set.

Fix: Update to version 4.9.11 or later. According to the source, this version patches the vulnerability by restricting the allowed system calls to a safer subset and adding additional descriptive error messaging.

NVD/CVE Database

CVE-2025-49619: Skyvern through 0.1.85 is vulnerable to server-side template injection (SSTI) in the Prompt field of workflow blocks suc

highvulnerability
security
Jun 7, 2025
CVE-2025-49619EPSS: 66.4%

CVE-2025-5018: The Hive Support plugin for WordPress is vulnerable to unauthorized access and modification of data due to a missing cap

highvulnerability
security
Jun 6, 2025
CVE-2025-5018

The Hive Support plugin for WordPress has a security flaw in versions up to 1.2.4 where two functions lack capability checks (security checks that verify user permissions). This allows attackers with basic Subscriber-level accounts to read and change the site's OpenAI API key, inspect data, and modify how the AI chatbot behaves.

CVE-2025-48957: AstrBot is a large language model chatbot and development framework. A path traversal vulnerability present in versions

highvulnerability
security
Jun 2, 2025
CVE-2025-48957

AstrBot, a chatbot and development framework powered by large language models (LLMs, AI systems trained on large amounts of text data), has a path traversal vulnerability (a flaw that lets attackers access files they shouldn't be able to reach) in versions 3.4.4 through 3.5.12 that could expose sensitive information like API keys (credentials used to access external services) and passwords. The vulnerability was fixed in version 3.5.13.

CVE-2025-48944: vLLM is an inference and serving engine for large language models (LLMs). In version 0.8.0 up to but excluding 0.9.0, th

mediumvulnerability
security
May 30, 2025
CVE-2025-48944

vLLM (a system for running and serving large language models) versions 0.8.0 through 0.9.0 have a vulnerability where the /v1/chat/completions API endpoint doesn't properly check user input in the 'pattern' and 'type' fields when the tools feature is used, allowing a single malformed request to crash the inference worker (the part that actually runs the model) until someone restarts it.

CVE-2025-48943: vLLM is an inference and serving engine for large language models (LLMs). Version 0.8.0 up to but excluding 0.9.0 have a

mediumvulnerability
security
May 30, 2025
CVE-2025-48943

CVE-2025-48943 is a Denial of Service vulnerability (a type of attack that crashes a system) in vLLM versions 0.8.0 through 0.8.x that causes the server to crash when given an invalid regex (a pattern used to match text). This happens specifically when using the structured output feature, which lets the AI format responses in a specific way.

CVE-2025-48942: vLLM is an inference and serving engine for large language models (LLMs). In versions 0.8.0 up to but excluding 0.9.0, h

mediumvulnerability
security
May 30, 2025
CVE-2025-48942

vLLM (an inference and serving engine for large language models) versions 0.8.0 through 0.8.x have a vulnerability where sending an invalid JSON schema as a parameter to the /v1/completions API endpoint causes the server to crash. This happens because the application doesn't properly handle (catch) exceptions that occur when processing malformed input.

CVE-2025-48887: vLLM, an inference and serving engine for large language models (LLMs), has a Regular Expression Denial of Service (ReDo

mediumvulnerability
security
May 30, 2025
CVE-2025-48887

vLLM, a software system that runs and serves large language models, has a vulnerability in how it parses tool commands that can be exploited to crash or slow down the service. The problem comes from using an overly complex pattern-matching rule (regular expression with nested quantifiers, optional groups, and inner repetitions) that can cause the system to get stuck processing certain inputs, leading to severe performance problems.

CVE-2025-48889: Gradio is an open-source Python package that allows quick building of demos and web application for machine learning mod

mediumvulnerability
security
May 30, 2025
CVE-2025-48889

Gradio is an open-source Python package for building machine learning demos and web applications. Before version 5.31.0, a vulnerability in its flagging feature let unauthenticated attackers copy any readable file from the server's filesystem, which could cause DoS (denial of service, where a system becomes unavailable) by copying massive files to fill up disk space, though attackers couldn't actually read the copied files.

CVE-2025-48491: Project AI is a platform designed to create AI agents. Prior to the pre-beta version, a hardcoded API key was present in

highvulnerability
security
May 30, 2025
CVE-2025-48491

CVE-2025-48491 is a vulnerability in Project AI, a platform for creating AI agents, where a hardcoded API key (a secret credential stored directly in the code rather than kept separate) was exposed in versions before the pre-beta release. This means attackers could potentially find and misuse this key to access the system without proper authorization.

CVE-2025-46722: vLLM is an inference and serving engine for large language models (LLMs). In versions starting from 0.7.0 to before 0.9.

mediumvulnerability
security
May 29, 2025
CVE-2025-46722

vLLM (a system for running large language models) versions 0.7.0 through 0.8.x have a bug in how they create hash values (fingerprints) for images. The hashing method only looks at the raw pixel data and ignores important image properties like width and height, so two different-sized images with the same pixels would create identical hash values. This can cause the system to incorrectly reuse cached results or expose data it shouldn't.

CVE-2025-46570: vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.9.0, when a new prompt is p

lowvulnerability
security
May 29, 2025
CVE-2025-46570

vLLM, an inference and serving engine for large language models, had a vulnerability in versions before 0.9.0 where timing differences in the PageAttention mechanism (a feature that speeds up processing by reusing matching text chunks) were large enough that attackers could detect and exploit them. This type of attack is called a timing side-channel attack, where an attacker learns information by measuring how long operations take.

CVE-2025-5320: A vulnerability classified as problematic has been found in gradio-app gradio up to 5.29.1. This affects the function is

lowvulnerability
security
May 29, 2025
CVE-2025-5320

A vulnerability (CVE-2025-5320) was found in Gradio, a web framework for building AI demos, affecting versions up to 5.29.1. An attacker could manipulate the localhost_aliases parameter in the CORS Handler (the component that controls which websites can access the application) to gain elevated privileges, though executing this attack is difficult and requires remote access.

CVE-2025-5277: aws-mcp-server MCP server is vulnerable to command injection. An attacker can craft a prompt that once accessed by the M

criticalvulnerability
security
May 28, 2025
CVE-2025-5277

CVE-2025-5277 is a command injection vulnerability (a flaw where an attacker can trick a program into running unwanted commands) in aws-mcp-server, an MCP server (a software tool that helps AI systems interact with AWS cloud services). An attacker can craft a malicious prompt that, when accessed by an MCP client (a program that connects to the server), executes arbitrary commands on the host system, with a critical severity rating of 9.4.

CVE-2025-47277: vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4 tha

criticalvulnerability
security
May 20, 2025
CVE-2025-47277

vLLM versions 0.6.5 through 0.8.4 have a vulnerability when using `PyNcclPipe` (a tool for peer-to-peer communication between multiple computers running the AI model) with the V0 engine. The issue is that a network communication interface called `TCPStore` was listening on all network connections instead of just the private network specified by the `--kv-ip` parameter, potentially exposing the system to unauthorized access.

CVE-2025-46725: Langroid is a Python framework to build large language model (LLM)-powered applications. Prior to version 0.53.15, `Lanc

criticalvulnerability
security
May 20, 2025
CVE-2025-46725

Langroid, a Python framework for building AI applications, has a vulnerability in versions before 0.53.15 where the `LanceDocChatAgent` component uses pandas eval() (a function that executes Python code stored in strings) in an unsafe way, allowing attackers to run malicious commands on the host system. The vulnerability exists in the `compute_from_docs()` function, which processes user queries without proper protection.

CVE-2025-46724: Langroid is a Python framework to build large language model (LLM)-powered applications. Prior to version 0.53.15, `Tabl

criticalvulnerability
security
May 20, 2025
CVE-2025-46724

Langroid, a Python framework for building LLM-powered applications, had a code injection vulnerability (CWE-94, a flaw where untrusted input can be executed as code) in its `TableChatAgent` component before version 0.53.15 because it used `pandas eval()` without proper safeguards. This could allow attackers to run arbitrary code if the application accepted untrusted user input.

CVE-2025-43714: The ChatGPT system through 2025-03-30 performs inline rendering of SVG documents (instead of, for example, rendering the

mediumvulnerability
security
May 19, 2025
CVE-2025-43714

ChatGPT through March 30, 2025, renders SVG documents (scalable vector graphics, a type of image format) directly in web browsers instead of displaying them as plain text, which allows attackers to inject HTML (the code that structures web pages) and potentially trick users through phishing attacks.

CVE-2025-2099: A vulnerability in the `preprocess_string()` function of the `transformers.testing_utils` module in huggingface/transfor

highvulnerability
security
May 19, 2025
CVE-2025-2099

A vulnerability in the `preprocess_string()` function of the huggingface/transformers library (version v4.48.3) allows a ReDoS attack (regular expression denial of service, where a poorly written pattern causes the computer to do exponential amounts of work). An attacker can send specially crafted input with many newline characters that makes the function use excessive CPU, potentially crashing the application.

CVE-2025-1975: A vulnerability in the Ollama server version 0.5.11 allows a malicious user to cause a Denial of Service (DoS) attack by

mediumvulnerability
security
May 16, 2025
CVE-2025-1975

CVE-2025-1975 is a vulnerability in Ollama server version 0.5.11 that allows an attacker to crash the server through a Denial of Service attack by sending specially crafted requests to the /api/pull endpoint (the function that downloads AI models). The vulnerability stems from improper validation of array index access (CWE-129, which means the program doesn't properly check if it's trying to access memory locations that don't exist), which happens when a malicious user customizes manifest content and spoofs a service.

Previous30 / 74Next

Skyvern through version 0.1.85 has a vulnerability where attackers can inject malicious code into the Prompt field of workflow blocks through SSTI (server-side template injection, where untrusted input is processed as code by the server's template engine). Authenticated users can craft special expressions in Jinja2 templates (a template system that evaluates code on the server) that aren't properly cleaned up, allowing them to execute commands on the server without direct feedback, a capability known as blind RCE (remote code execution).

Fix: A fix is referenced in the GitHub commit db856cd8433a204c8b45979c70a4da1e119d949d in the Skyvern repository, but the source text does not explicitly describe what the fix does or provide a specific patched version number to upgrade to.

NVD/CVE Database
NVD/CVE Database

Fix: Upgrade to version 3.5.13 or later. As a temporary workaround, users can edit the `cmd_config.json` file to disable the dashboard feature.

NVD/CVE Database

Fix: Update to version 0.9.0 or later, which fixes the issue.

NVD/CVE Database

Fix: Upgrade to version 0.9.0, which fixes the issue. A patch is available at https://github.com/vllm-project/vllm/commit/08bf7840780980c7568c573c70a6a8db94fd45ff.

NVD/CVE Database

Fix: Update to vLLM version 0.9.0 or later, which fixes the issue.

NVD/CVE Database

Fix: Update to version 0.9.0 or later, which contains a patch for the issue.

NVD/CVE Database

Fix: Update to Gradio version 5.31.0 or later, where this issue has been patched.

NVD/CVE Database
NVD/CVE Database

Fix: This issue has been patched in version 0.9.0.

NVD/CVE Database

Fix: Update vLLM to version 0.9.0 or later. The issue has been patched in version 0.9.0.

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

Fix: Update to vLLM version 0.8.5 or later. According to the source: "As of version 0.8.5, vLLM limits the `TCPStore` socket to the private interface as configured."

NVD/CVE Database

Fix: Upgrade to Langroid version 0.53.15 or later. The fix involves input sanitization (cleaning and filtering user input) to the affected function by default to block common attack vectors, along with added warnings in the project documentation about the risky behavior.

NVD/CVE Database

Fix: Upgrade to Langroid version 0.53.15 or later. According to the source, 'Langroid 0.53.15 sanitizes input to `TableChatAgent` by default to tackle the most common attack vectors, and added several warnings about the risky behavior in the project documentation.'

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