Live Incident Intelligence

The article highlights critical security gaps in Large Language Model (LLM) applications, detailing common vulnerabilities such as prompt injection, sensitive information disclosure, and supply chain compromises. These flaws, categorized by the OWASP Top 10 for LLM Applications, can lead to unintended LLM behavior, data exposure, and other serious consequences.

A critical "EchoLeak" zero-click vulnerability in Microsoft 365 Copilot allowed attackers to remotely exfiltrate sensitive internal data by sending emails containing hidden instructions. This flaw represents an LLM scope violation where the AI agent was tricked into accessing information beyond its intended permissions without user interaction.

A remotely exploitable zero-day vulnerability, CVE-2025-37899, has been discovered in the Linux kernel's Server Message Block (SMB) protocol using OpenAI's o3 model. This critical flaw is identified as a use-after-free bug in the SMB 'logoff' command handler, allowing an object to be freed while still accessible by another thread.

The DeepSeek breach reportedly resulted in sensitive data being exposed to the dark web, indicating a significant impact on data confidentiality. The full article content detailing the specific exploit or incident scope was not successfully retrieved due to a Cloudflare security block during the scraping process.

In Langchain before 0.0.329, prompt injection allows an attacker to force the service to retrieve data from an arbitrary URL, essentially providing SSRF and potentially injecting content into downstream tasks.

SQL injection vulnerability in langchain allows a remote attacker to obtain sensitive information via the SQLDatabaseChain component.