643 matches found
CVE-2024-53844
CVE-2024-53844 affects labsai/eddi (EDDI), a middleware for LLM API bots. The vulnerability is a path traversal in the backup export functionality, exploitable via the botFilename parameter in RestExportService.java. Input is not properly sanitized, allowing attackers to access arbitrary files in...
AI Under the Microscope—What’s Changed in the OWASP Top 10 for LLMs 2025
As AI continues to evolve, so do the threats and vulnerabilities that surround Large Language Models LLMs. The OWASP Top 10 for LLM Applications 2025 introduces critical updates that reflect the rapid changes in how these models are applied in real-world scenarios. While the list includes...
Flowise OverrideConfig security vulnerability
Impact Flowise allows developers to inject configuration into the Chainflow during execution through the overrideConfig option. This is supported in both the frontend web integration and the backend Prediction API. This has a range of fundamental issues that are a major security vulnerability...
CVE-2024-4343 Python Command Injection in imartinez/privategpt
A Python command injection vulnerability exists in the SagemakerLLM class's complete method within ./privategpt/components/llm/custom/sagemaker.py of the imartinez/privategpt application, versions up to and including 0.3.0. The vulnerability arises due to the use of the eval function to parse a...
CVE-2024-4343
The CVE-2024-4343 entry describes a Python command injection in the imartinez/privategpt project. Affected component: SagemakerLLM.complete() in ./private_gpt/components/llm/custom/sagemaker.py, with versions up to and including 0.3.0. Root cause: unsafe parsing of a remote SageMaker LLM endpoint...
AIOps - Revolutionizing Incident Management with Advanced Automation and LLM Integration
AIOps - Revolutionizing Incident Management with Advanced Automation and LLM Integration By Trellix · November 14, 2024 Contributed by Chalapathy Jampal, Siddhesh Shinde, Alagiri Annadurai, Lakshmi Ram Teja Eluri and Anil Pokhrel Managing infrastructure and applications across a complex IT...
Prompt Injection Defenses Against LLM Cyberattacks
Interesting research: "Hacking Back the AI-Hacker: Prompt Injection as a Defense Against LLM-driven Cyberattacks": Large language models LLMs are increasingly being harnessed to automate cyberattacks, making sophisticated exploits more accessible and scalable. In response, we propose a new defens...
Google's AI Tool Big Sleep Finds Zero-Day Vulnerability in SQLite Database Engine
Google said it discovered a zero-day vulnerability in the SQLite open-source database engine using its large language model LLM assisted framework called Big Sleep formerly Project Naptime. The tech giant described the development as the "first real-world vulnerability" uncovered using the...
CVE-2024-7783 Improper Storage of Sensitive Information in Bearer Token in mintplex-labs/anything-llm
mintplex-labs/anything-llm version latest contains a vulnerability where sensitive information, specifically a password, is improperly stored within a JWT JSON Web Token used as a bearer token in single user mode. When decoded, the JWT reveals the password in plaintext. This improper storage of...
Watermark for LLM-Generated Text
Researchers at Google have developed a watermark for LLM-generated text. The basics are pretty obvious: the LLM chooses between tokens partly based on a cryptographic key, and someone with knowledge of the key can detect those choices. What makes this hard is 1 how much text is required for the...
CVE-2024-10131 Remote Code Execution in infiniflow/ragflow
The addllm function in llmapp.py in infiniflow/ragflow version 0.11.0 contains a remote code execution RCE vulnerability. The function uses user-supplied input req'llmfactory' and req'llmname' to dynamically instantiate classes from various model dictionaries. This approach allows an attacker to...
RAGFlow 命令注入漏洞
RAGFlow is an open source RAG engine based on deep document understanding from InfiniFlow Open Source. A command injection vulnerability exists in RAGFlow version 0.11.0, which stems from a lack of comprehensive input validation or cleanup, causing the addllm function in llmapp.py to contain a...
PT-2024-10269 · Unknown · Llm Lunary
Name of the Vulnerable Software and Affected Versions: LLM Lunary affected versions not specified Description: The issue is related to insufficient access control mechanisms in the LLM Lunary platform, which is used for monitoring, managing, and improving applications. This can be exploited by a...
PT-2024-16051 · Infiniflow · Ragflow
Name of the Vulnerable Software and Affected Versions: infiniflow/ragflow version 0.11.0 Description: The issue concerns a remote code execution vulnerability in the add llm function, located in llm app.py. This function utilizes user-supplied input, specifically req'llm factory' and req'llm name...
AI/LLM Claude Sonnet API Detection
Binary data 701487.prm...
AI/LLM Google Gemini API Detection
Binary data 701488.prm...
AI/LLM Matroid AI Detection
Binary data 701484.prm...
AI/LLM Bettybot Domain Detection
Binary data 701483.prm...