AI & LLM Vulnerabilities

n8n-mcp versions before 2.50.1 had three security issues: unvalidated workflow IDs allowed attackers to bypass access controls and leak API keys, webhook URLs followed redirects to unintended hosts (SSRF, a type of attack where a server makes unwanted requests to other systems), and telemetry (usage data sent to developers) stored sensitive information like API keys without hiding it. The vulnerability has a CVSS score (a 0-10 rating of how severe a vulnerability is) of 8.3 and requires an authenticated attacker with access to the n8n API.

An authenticated SSRF (server-side request forgery, where an attacker tricks a server into making unwanted requests to internal services) vulnerability affects n8n-mcp's webhook and API client features. An attacker with access to the system can make the n8n-mcp host send HTTP requests to internal services or cloud credential endpoints that should be blocked, allowing them to steal credentials or enumerate internal systems.

Langfuse, an open source platform for managing large language models, had a role-based access control flaw (a security issue where user permissions weren't properly enforced) in versions 3.68.0 through 3.166.9 that allowed low-privileged project members to redirect API requests to attacker-controlled servers, potentially exposing sensitive API keys. The vulnerability required the attacker to already have basic access to a project as a member.

PromptHub versions 0.4.9 to before 0.5.4 contain an SSRF vulnerability (server-side request forgery, where an attacker tricks the server into fetching URLs they control). An authenticated endpoint allows users to supply a URL that the server fetches and returns the response, but the security check meant to block private IP addresses (internal network addresses) can be bypassed using alternate IPv6 (internet protocol version 6, the newer internet addressing system) representations. Any registered user can exploit this, or anyone on the internet if registration is enabled.

LiteLLM, a proxy server (intermediary program that forwards requests to different AI APIs) versions 1.81.16 through 1.83.6, has a SQL injection vulnerability (a flaw where attackers insert malicious code into database queries by manipulating user inputs). An unauthenticated attacker could craft a fake Authorization header to read or modify data stored in the proxy's database, potentially gaining unauthorized access to stored API credentials.

CVE-2026-35435 is a vulnerability in Azure AI Foundry M365 published agents where improper access control (weak rules about who can access what) allows an unauthorized attacker to gain higher privileges over a network. The vulnerability has a CVSS score (a 0-10 rating of how severe a vulnerability is) assessment that has not yet been provided by NIST.

CVE-2026-33111 is a command injection vulnerability (where an attacker inserts malicious commands into user input) in Copilot Chat for Microsoft Edge that could allow an unauthorized attacker to disclose information over a network. The vulnerability stems from improper handling of special characters in commands. No severity score has been assigned yet by NIST.

CVE-2026-32207 is a cross-site scripting vulnerability (XSS, where an attacker injects malicious code into a web page that gets executed in users' browsers) in Azure Machine Learning that allows an unauthorized attacker to perform spoofing (impersonating someone or something else) over a network. The vulnerability stems from improper handling of user input during web page generation.

CVE-2026-26164 is a vulnerability in Microsoft 365 Copilot caused by improper neutralization of special elements in output (a type of injection attack, where specially crafted input can be misinterpreted as commands). An attacker without authorization could exploit this to access and disclose information over a network.

CVE-2026-26129 is a vulnerability in Microsoft 365 Copilot where improper neutralization of special elements (failure to safely handle certain characters or code) allows an unauthorized attacker to disclose information over a network. The vulnerability has a CVSS score (a 0-10 rating of how severe a vulnerability is) of 4.0, indicating moderate severity.

Diffusers, a popular AI library, had a security flaw where the `trust_remote_code` parameter (a safety check to prevent running untrusted code) could be bypassed in three ways when loading models with `DiffusionPipeline.from_pretrained()`. An attacker could execute arbitrary code on a user's machine even when the user explicitly set `trust_remote_code=False` or left it at its default safe setting. The vulnerability affected users loading custom pipelines (external code) or local model snapshots (saved model files).

The Diffusers library has a vulnerability where arbitrary code can be silently executed when loading a pipeline from HuggingFace Hub, bypassing the `trust_remote_code` security check. An attacker can craft a repository with custom code in a Python file that gets automatically executed during `DiffusionPipeline.from_pretrained()` without requiring the `trust_remote_code=True` parameter or any visible warning, allowing remote code execution (RCE, where an attacker runs commands on a system they don't own).

Keras has a critical vulnerability in its model loader (KerasFileEditor) that allows attackers to cause a Denial of Service (DoS, where a system becomes unusable) by uploading malicious .keras files. An attacker can craft a small .keras file (100-400 KB) that declares an extremely large dataset shape in its HDF5 weight file (a binary format for storing weights in neural networks), but stores only a few bytes of actual data. When Keras loads this file, it attempts to allocate petabytes of RAM based on the declared shape, immediately crashing the system and killing any applications processing the model.