CVE-2025-69222 LibreChat is vulnerable to Server-Side Request Forgery due to missing restrictions

LibreChat is a ChatGPT clone with additional features. Version 0.8.1-rc2 is prone to a server-side request forgery SSRF vulnerability due to missing restrictions of the Actions feature in the default configuration. LibreChat enables users to configure agents with predefined instructions and actio...

CVE-2025-69222

CVE-2025-69222 affects LibreChat (v0.8.1-rc2 and prior) with a server-side request forgery (SSRF) due to missing restrictions in the default Actions configuration. The issue arises because agents can be configured with predefined instructions and actions via OpenAPI, enabling access to arbitrary ...

CVE-2025-69222 LibreChat is vulnerable to Server-Side Request Forgery due to missing restrictions

LibreChat is a ChatGPT clone with additional features. Version 0.8.1-rc2 is prone to a server-side request forgery SSRF vulnerability due to missing restrictions of the Actions feature in the default configuration. LibreChat enables users to configure agents with predefined instructions and actio...

CVE-2025-69286

RAGFlow is an open-source RAG Retrieval-Augmented Generation engine. In versions prior to 0.22.0, the use of an insecure key generation algorithm in the API key and beta assistant/agent share auth token generation process allows these tokens to be mutually derivable. Specifically, both tokens are...

EUVD-2025-7088

Malicious code in bioql PyPI...

EUVD-2025-5395

Malicious code in bioql PyPI...

Langflow 安全漏洞

Langflow is a visualization framework for building multi-agent and RAG applications open-sourced by Langflow. A security vulnerability exists in Langflow that stems from improper management of permissions within a container, which could lead to elevation of privilege...

pgai 信息泄露漏洞

pgai is a set of tools open-sourced by timescale to make it easier to develop RAG, semantic search, and other AI applications using PostgreSQL. An information disclosure vulnerability exists in pgai, which stems from a vulnerability that allows an attacker to steal all secrets in a workflow...

Langflow Chatbot Detected

This is an informational plugin to inform the user that the scanner has detected a publicly accessible Langflow chatbot on the target application. Langflow is an open-source visual framework for building multi-agent and RAG. This detection is included in the AI and LLM category. No source data...

Benchmarking Poisoning Attacks against Retrieval-Augmented Generation

Retrieval-Augmented Generation RAG has proven effective in mitigating hallucinations in large language models by incorporating external knowledge during inference. However, this integration introduces new security vulnerabilities, particularly to poisoning attacks. Although prior work has explore...

Securing RAG: a Risk Assessment and Mitigation Framework

Retrieval Augmented Generation RAG has emerged as the de facto industry standard for user-facing NLP applications, offering the ability to integrate data without re-training or fine-tuning Large Language Models LLMs. This capability enhances the quality and accuracy of responses but also introduc...

ARCeR: an Agentic RAG for the Automated Definition of Cyber Ranges

The growing and evolving landscape of cybersecurity threats necessitates the development of supporting tools and platforms that allow for the creation of realistic IT environments operating within virtual, controlled settings as Cyber Ranges CRs. CRs can be exploited for analyzing vulnerabilities...

CVE-2024-10834

eosphoros-ai/db-gpt version 0.6.0 contains a vulnerability in the RAG-knowledge endpoint that allows for arbitrary file write. The issue arises from the ability to pass an absolute path to a call to os.path.join, enabling an attacker to write files to arbitrary locations on the target server. Thi...

CVE-2024-10834

eosphoros-ai/db-gpt version 0.6.0 contains a vulnerability in the RAG-knowledge endpoint that allows for arbitrary file write. The issue arises from the ability to pass an absolute path to a call to os.path.join, enabling an attacker to write files to arbitrary locations on the target server. Thi...

CVE-2024-10834 Arbitrary File Write in eosphoros-ai/db-gpt

eosphoros-ai/db-gpt version 0.6.0 contains a vulnerability in the RAG-knowledge endpoint that allows for arbitrary file write. The issue arises from the ability to pass an absolute path to a call to os.path.join, enabling an attacker to write files to arbitrary locations on the target server. Thi...

CVE-2024-10834

CVE-2024-10834 affects eosphoros-ai/db-gpt version 0.6.0, with a vulnerability in the RAG-knowledge endpoint that permits arbitrary file write by passing an absolute path to os.path.join via doc_file.filename. Attackers could write to arbitrary locations on the target server, potentially overwrit...

CVE-2024-10834 Arbitrary File Write in eosphoros-ai/db-gpt

eosphoros-ai/db-gpt version 0.6.0 contains a vulnerability in the RAG-knowledge endpoint that allows for arbitrary file write. The issue arises from the ability to pass an absolute path to a call to os.path.join, enabling an attacker to write files to arbitrary locations on the target server. Thi...

Malicious code in dvd-ai-pc-rag (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware a767db3d0d8194ea0442ea2138060477dfc8356ba986a5e7a707145af45d9427 Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

MAL-2025-2378 Malicious code in dvd-ai-pc-rag (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware a767db3d0d8194ea0442ea2138060477dfc8356ba986a5e7a707145af45d9427 Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

Malicious code in auth0-langgraph-state-rag-js (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 4726a148bd39bb68771231f6ed71f2edab6932f2f9468e69b5f659528ebb6d4f Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...