Browse All

Gradio, an open-source Python package for building AI interfaces quickly, has a vulnerability where the enable_monitoring flag doesn't actually disable monitoring as intended. Even when a developer sets enable_monitoring=False to turn off monitoring, an attacker can still access sensitive analytics by directly requesting the /monitoring endpoint (a specific web address). This puts applications at risk of exposing data that was supposed to be hidden.

Gradio, an open-source Python package for building quick demos, has a vulnerability called path traversal (a method where attackers manipulate file paths to access files outside their intended directory) in its `/custom_component` endpoint. Attackers can exploit this to read and leak source code from custom Gradio components, potentially exposing sensitive code that developers wanted to keep private, particularly affecting those hosting custom components on public servers.

Gradio, an open-source Python package for building AI demos, has a vulnerability where it incorrectly accepts requests from sources with a null origin (a security boundary used by web browsers). This happens because the `localhost_aliases` variable includes "null" as a valid CORS origin (cross-origin resource sharing, which controls what websites can access a server). Attackers could exploit this to steal sensitive data like login tokens or uploaded files from local Gradio deployments.

Gradio, an open-source Python package for building AI demos, has a vulnerability in its directory traversal check function that can be bypassed using special file path sequences (like `..` which means "go up one folder"). This could allow attackers to access files they shouldn't be able to reach, especially when uploading files, though exploiting it is difficult.

Taipy, an open-source Python library for building data applications, has a security flaw where session cookies are served without the Secure and HTTPOnly flags (security markers that prevent browsers from sending cookies over unencrypted connections and protect cookies from being accessed by JavaScript code). This vulnerability has a CVSS score (a 0-10 rating of how severe a vulnerability is) of 6.3, indicating medium severity.

CVE-2024-9333 is a permissions bypass vulnerability in M-Files Connector for Copilot (a tool that integrates M-Files document management with AI assistants) that allows authenticated users (people who have already logged in) to access documents they shouldn't be able to see due to incorrect access control list calculations. The vulnerability has a CVSS score of 5.3 (a 0-10 rating of how severe a vulnerability is), which is rated as medium severity.

CVE-2024-0116 is a vulnerability in NVIDIA Triton Inference Server that allows a user to trigger an out-of-bounds read (accessing memory outside the intended range) by releasing a shared memory region while another part of the program is still using it. A successful attack could cause a denial of service (making the service unavailable), though the severity rating has not yet been officially assigned.

Monica AI Assistant desktop application v2.3.0 has a vulnerability where attackers can use prompt injection (tricking an AI by hiding instructions in its input) with a specially crafted image to steal sensitive chat data from the current session and send it to an attacker-controlled server. This flaw allows unauthorized people to access private information from users' conversations.

CVE-2024-40441 is a privilege escalation vulnerability (a bug that lets attackers gain higher-level access than they should have) in Doccano v.1.8.4, an open source tool for labeling data to train machine learning models, and its Auto Labeling Pipeline module v.0.1.23. A remote attacker can exploit this by manipulating the model_attribs parameter to escalate their privileges.