GHSA-M4RF-3FR8-XWX3 vulnerabilities

Vulnerabilities for packages: nemo, open-webui...

CVE-2026-8447

IBM Langflow OSS 1.0.0 through 1.11.2 suffer from a stored cross-site scripting vulnerability in the Playground chat interface...

CVE-2026-84287

A flaw has been found in NousResearch hermes-agent 0.18.0. Affected by this issue is some unknown functionality of the file gateway/platforms/apiserver.py of the component Session Chat Interface. This manipulation causes denial of service. The attack is possible to be carried out remotely. The...

CVE-2026-84287

A denial-of-service vulnerability exists in NousResearch hermes-agent 0.18.0 , specifically within the Session Chat Interface component in the file gateway/platforms/api_server.py. The flaw allows a remote attacker with low privileges to cause a service disruption. The exploit is reported as publ...

EUVD-2026-69699

A flaw has been found in NousResearch hermes-agent 0.18.0. Affected by this issue is some unknown functionality of the file gateway/platforms/apiserver.py of the component Session Chat Interface. This manipulation causes denial of service. The attack is possible to be carried out remotely. The...

PT-2026-84514

Name of the Vulnerable Software and Affected Versions hermes-agent version 0.18.0 Description A flaw in the Session Chat Interface component, specifically within the gateway/platforms/api server.py file, allows a remote attacker to cause a denial of service. Recommendations At the moment, there i...

MAL-2026-11936 Malicious code in @servicetitan/titan-chat-ui-anvil2 (npm)

npm/@servicetitan/titan-chat-ui-anvil2 is affected by the large-scale, self-propagating npm supply-chain worm of 2026-08-04 the "Shai-Hulud: Here We Go Again" wave — the same campaign that began with the compromise of the keyv and cacheable maintainer account. The listed versions were trojanized...

CVE-2026-47470

CVE-2026-47470 affects NVIDIA TensorRT-LLM on any platform, via a vulnerability in the gRPC server chat API endpoint. The root cause is improper input validation, exploitable by a local attacker to cause a denial of service. The NVIDIA security bulletin lists remediation by updating to TensorRT-L...

CVE-2026-47470

NVIDIA TensorRT-LLM for any platform contains a vulnerability in the gRPC server chat API endpoint, where an attacker could cause CWE-20 by local attack. A successful exploit of this vulnerability might lead to denial of service...

Directory Traversal

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...

CVE-2026-61445

Summary (CVE-2026-61445) PraisonAI prior to 4.6.78 exposes arbitrary file write and command execution via the AICoder component. The root cause is missing path validation and lack of command sanitization in LLM tool calls, enabling an attacker to inject malicious prompts through the chat interfac...

EUVD-2026-43181

PraisonAI before 4.6.78 contains arbitrary file write and command execution vulnerabilities in the AICoder component due to missing path validation and command sanitization in LLM tool calls. Attackers can inject malicious prompts through the chat interface to write files to arbitrary filesystem...

CVE-2026-54771

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.3, a Langroid application exposing a chat interface to untrusted users may allow direct tool invocation via raw JSON payloads, even when tools are registered with use=False, handle=True. Version...

CVE-2026-54771

Langroid prior to 0.65.3 is affected. A Langroid application exposing a chat interface to untrusted users may allow direct tool invocation via raw JSON payloads, even when tools are registered with use=False, handle=True. Root cause: the tool dispatch path in agent_response → handle_message → get...

DRUPAL-CONTRIB-2026-068

This module enables you to test and run AI-driven workflows interactively through a chat interface. The module doesn't sufficiently re-evaluate a human-in-the-loop approval gate where the workflow iterates more than once. This may result in execution of workflows that were not intended by the use...

DRUPAL-CONTRIB-2026-067

This module enables you to test and run AI-driven workflows interactively through a chat interface. The module doesn't sufficiently enforce permissions on certain endpoints. Attackers may be able to trigger workflow execution incurring LLM spend and tool side effects or send messages into other...

PT-2026-55225

Name of the Vulnerable Software and Affected Versions FlowDrop versions 0.0.0 through 1.6.0 Description A missing authorization issue allows forceful browsing. The module, which enables testing and running AI-driven workflows via a chat interface, fails to sufficiently re-evaluate human-in-the-lo...

CVE-2026-58116

LLaMA-Factory through 0.9.5 contains a remote code execution vulnerability that allows attackers with WebUI access to execute arbitrary Python code by supplying a malicious model path in the Chat or Training interfaces. The application passes user-supplied model path input unvalidated into...

EUVD-2026-40311

LLaMA-Factory through 0.9.5 contains a remote code execution vulnerability that allows attackers with WebUI access to execute arbitrary Python code by supplying a malicious model path in the Chat or Training interfaces. The application passes user-supplied model path input unvalidated into...

CVE-2026-39423

MaxKB is an open-source AI assistant for enterprise. Versions 2.7.1 and below contain an Eval Injection vulnerability in the Markdown rendering engine that allows any user capable of interacting with the AI chat interface to execute arbitrary JavaScript in the browsers of other users, including...