7 HIGH · THREAT ORANGE · 7 items · Generated in 409s
A vulnerability in an open-source library for large language model inference could lead to data integrity issues.
vLLM versions contain multiple ReDoS vulnerabilities, allowing attackers to trigger denial of service.
vLLM versions are vulnerable to crashes and resource exhaustion due to missing sparse tensor validation.
LangChain framework has a vulnerability that allows disclosure of files outside the intended boundary when components receive path values from untrusted sources
Arbitrary code execution on the server via a malicious HuggingFace model.
Authenticated users can access unauthorized Ollama backends.
LLMs can be confused by subtle text modifications, leading to security vulnerabilities.