AnythingLLM Input Validation Error Vulnerability

AnythingLLM is a document chatbot that meets business requirements. An input validation error vulnerability exists in AnythingLLM that stems from the application failing to validate or check user input before passing it to the Prisma model for execution...

Mlflow Security Vulnerabilities

Mlflow is an open source platform for machine learning lifecycles. A security vulnerability exists in Mlflow that stems from the ability to create multiple models with the same name using URL encoding, potentially leading to a denial of service...

PT-2024-23711

Name of the Vulnerable Software and Affected Versions mlflow/mlflow version 2.11.1 Description A vulnerability in mlflow/mlflow allows attackers to create multiple models with the same name by exploiting URL encoding. This flaw can lead to Denial of Service DoS as an authenticated user might not ...

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...

LiteLLM Code Injection Vulnerability

LiteLLM is an open source application from Berri AI. All LLM APIs can be called using the OpenAI format. LiteLLM suffers from a code injection vulnerability that stems from insufficient cleaning and validation of model output data, leading to a stored cross-site scripting vulnerability...

PT-2024-25646 · Unknown · Gaizhenbiao/Chuanhuchatgpt

Name of the Vulnerable Software and Affected Versions: gaizhenbiao/chuanhuchatgpt version 20240121 Description: A stored Cross-Site Scripting XSS issue exists due to inadequate sanitization and validation of model output data. Despite user-input validation efforts, the application fails to proper...

Lunary 访问控制错误漏洞

lunary is a production toolkit for LLM. An access control error vulnerability exists in lunary that stems from insufficient validation of roles and permissions on the backend. An attacker could exploit this vulnerability to cause information disclosure...

PT-2024-24122 · Mintplex · Anything-Llm

Name of the Vulnerable Software and Affected Versions: mintplex-labs/anything-llm affected versions not specified Description: A vulnerability exists in the thread update process, allowing users with Default or Manager roles to escalate their privileges to Administrator. This issue arises from...

Securing AI Development in the Cloud: Navigating the Risks and Opportunities

AI-TRiSM - Trust, Risk and Security Management in the Age of AI Co-authored by Lara Sunday and Pojan Shahrivar As artificial intelligence AI and machine learning ML technologies continue to advance and proliferate, organizations across industries are investing heavily in these transformative...

Online Privacy and Overfishing

Microsoft recently caught state-backed hackers using its generative AI tools to help with their attacks. In the security community, the immediate questions werent about how hackers were using the tools that was utterly predictable, but about how Microsoft figured it out. The natural conclusion wa...

EmailGPT Security Vulnerabilities

EmailGPT is a Google Chrome extension by individual developer Nasrullah in Singapore that helps users compose emails in Gmail using OpenAI's GPT-3.5 model. A security vulnerability exists in EmailGPT that stems from the inclusion of a prompt injection vulnerability...

AI jailbreaks: What they are and how they can be mitigated

Generative AI systems are made up of multiple components that interact to provide a rich user experience between the human and the AI models. As part of a responsible AI approach, AI models are protected by layers of defense mechanisms to prevent the production of harmful content or being used to...

Skops unsafe deserialization

Deserialization of untrusted data can occur in versions 0.6 or newer of the skops python library, enabling a maliciously crafted model to run arbitrary code on an end user's system when loaded...

GHSA-WF7F-8FXF-XFXC MLFlow unsafe deserialization

Deserialization of untrusted data can occur in versions of the MLflow platform running version 0.5.0 or newer, enabling a maliciously uploaded PyTorch model to run arbitrary code on an end user’s system when interacted with...

GHSA-J8MG-PQC5-X9GJ MLFlow unsafe deserialization

Deserialization of untrusted data can occur in versions of the MLflow platform running version 2.0.0rc0 or newer, enabling a maliciously uploaded Tensorflow model to run arbitrary code on an end user’s system when interacted with...

MLFlow unsafe deserialization

Deserialization of untrusted data can occur in versions of the MLflow platform running version 1.24.0 or newer, enabling a maliciously uploaded pmdarima model to run arbitrary code on an end user’s system when interacted with...

GHSA-GHV6-9R9J-WH4J MLFlow unsafe deserialization

Deserialization of untrusted data can occur in versions of the MLflow platform running version 0.9.0 or newer, enabling a maliciously uploaded PyFunc model to run arbitrary code on an end user’s system when interacted with...

MLFlow unsafe deserialization

Deserialization of untrusted data can occur in versions of the MLflow platform running version 0.9.0 or newer, enabling a maliciously uploaded PyFunc model to run arbitrary code on an end user’s system when interacted with...

GHSA-7P8J-QV6X-F4G4 MLFlow unsafe deserialization

Deserialization of untrusted data can occur in versions of the MLflow platform running version 1.23.0 or newer, enabling a maliciously uploaded LightGBM scikit-learn model to run arbitrary code on an end user’s system when interacted with...

GHSA-X38X-G6GR-JQFF MLFlow unsafe deserialization

Deserialization of untrusted data can occur in versions of the MLflow platform running version 1.24.0 or newer, enabling a maliciously uploaded pmdarima model to run arbitrary code on an end user’s system when interacted with...