CVE-2026-28444

Typebot is a chatbot builder tool. In versions 3.15.2 and prior, the getResultLogs API endpoint authorizes the caller against the provided typebotId but fetches logs solely by resultId without verifying that the result belongs to the authorized typebot, leading to IDOR. An authenticated attacker...

The Governance Gap: How the EU AI Act Makes API Security a Compliance Imperative

Your legal team just handed you a 400-page document and said "figure out compliance." The EU AI Act is live, your organization falls under its scope, which is broader than many expect. Even non‑EU companies must comply if their AI systems are used, deployed, or produce effects within the European...

CVE-2026-28788

Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to version 0.8.6, any authenticated user can overwrite any file's content by ID through the POST /api/v1/retrieval/process/files/batch endpoint. The endpoint performs no ownership check, so a...

CVE-2026-32097

PingPong is a platform for using large language models LLMs for teaching and learning. Prior to 7.27.2, an authenticated user may be able to retrieve or delete files outside the intended authorization scope. This issue could result in retrieval or deletion of private files, including user-uploade...

CVE-2025-65368

SparkyFitness v0.15.8.2 is vulnerable to Cross Site Scripting XSS via user input and LLM output...

SparkyFitness security vulnerability

SparkyFitness is a fitness and health management platform developed by CodeWithCJ. Version SparkyFitness v0.15.8.2 contains a security vulnerability, which stems from improper handling of user input and LLM outputs, potentially leading to cross-site scripting attacks...

MalEval Android Malware Evaluation Framework

This repository contains the source code of MalEval, an evaluation framework for Android malware behavior auditing, focusing on explaining and substantiating malicious behaviors. The framework provides expert-verified reports, curated metadata, and model outputs to enable reproducible evaluation ...

AuthPrint: Fingerprinting Generative Models against Malicious Model Providers

Generative models are increasingly adopted in high-stakes domains, yet current deployments offer no mechanisms to verify the origin of model outputs. We address this gap by extending model fingerprinting techniques beyond the traditional collaborative setting to one where the model provider may a...

SoK: the Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation

Large language models LLMs are sophisticated artificial intelligence systems that enable machines to generate human-like text with remarkable precision. While LLMs offer significant technological progress, their development using vast amounts of user data scraped from the web and collected from...

Arbitrary Command Injection

Overview plotai is a Create plots in Python with AI Affected versions of this package are vulnerable to Arbitrary Command Injection in executor.py due to lack of validation of LLM-generated output. An attacker can supply code which will then be executed with Python's exec function. Remediation...

Race Condition Attacks against LLMs

These are two attacks against the system components surrounding LLMs: We propose that LLM Flowbreaking, following jailbreaking and prompt injection, joins as the third on the growing list of LLM attack types. Flowbreaking is less about whether prompt or response guardrails can be bypassed, and mo...

ChuanhuChatGPT Security Vulnerability

ChuanhuChatGPT is a light and easy-to-use Web GUI for ChatGPT/ChatGLM/LLaMA/StableLM/MOSS and many other LLMs. A security vulnerability exists in ChuanhuChatGPT, which stems from insufficient cleaning and validation of model output data, resulting in a stored cross-site scripting vulnerability...