CVE-2026-67989

crmne/rubyllm at commit fa6f279847d6d7027814539d9c0dfc3bbdfd2a83 contains a polynomial-time regular expression denial-of-service condition in Mistral model capability matching on Ruby 3.1.x...

CVE-2026-67989

crmne/rubyllm at commit fa6f279847d6d7027814539d9c0dfc3bbdfd2a83 contains a polynomial-time regular expression denial-of-service condition in Mistral model capability matching on Ruby 3.1.x...

CVE-2026-67989

crmne/rubyllm at commit fa6f279847d6d7027814539d9c0dfc3bbdfd2a83 contains a polynomial-time regular expression denial-of-service condition in Mistral model capability matching on Ruby 3.1.x...

CVE-2026-67989: Inefficient Regular Expression Complexity

crmne/rubyllm at commit fa6f279847d6d7027814539d9c0dfc3bbdfd2a83 contains a polynomial-time regular expression denial-of-service condition in Mistral model capability matching on Ruby 3.1.x...

CVE-2026-67989

The crmne/ruby_llm library (specifically at commit fa6f279847d6d7027814539d9c0dfc3bbdfd2a83 ) contains a polynomial-time regular expression denial-of-service (ReDoS) condition. This vulnerability exists within the Mistral model capability matching functionality when running on Ruby 3.1.x . The is...

Analysis of LLMs against Prompt Injection and Jailbreak Attacks

Large Language Models LLMs are widely deployed in real-world systems. Given their broader applicability, prompt engineering has become an efficient tool for resource-scarce organizations to adopt LLMs for their own purposes. At the same time, LLMs are vulnerable to prompt-based attacks. Thus,...