6 HIGH · 1 INFO · THREAT ORANGE · 7 items · Generated in 371s
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.
An unauthenticated remote information disclosure vulnerability allows an attacker to read and exfiltrate server's heap memory.
Remote code execution vulnerability in LLaMA-Factory allows attackers to execute arbitrary Python code.
Raytha CMS SQL Injection vulnerability allows remote attackers to execute arbitrary SQL statements and compromise the database.
A challenge to hack an AI assistant was run, with 6,000 attempts failing to leak secrets.