modelcontextprotocol/python-sdk incidents

Low severity NEW

AI Security Incident

CISA Flags First MCP Flaw: LiteLLM CVE-2026-59822 tech-insider.org

MCPCISA Flags FirstLiteLLM CVEMCP FlawBerriAI/litellmmodelcontextprotocol/python-sdk

1 source: news.google.com Updated 10h ago

Low severity STABLE

Google Authentication Bypass

New Gaslight macOS Malware Uses Prompt Injection to Disrupt AI-Assisted Analysis The Hacker News

AppleBraveGoogleMicrosoftMozillaOpenAI

2 sources: news.google.com, thehackernews.com Updated 13d ago

Low severity STABLE

Microsoft Copilot Remote Code Execution Vulnerability

Millions of AI agents imperiled by critical vulnerability in open source package Ars Technica

Amazon AWSAnthropicGitHubGoogleMicrosoftOpenAI

5 sources: news.google.com +4 Updated 13d ago

Low severity STABLE

Attackers Use LLM Agent for Post-Exploitation After Marimo CVE-2026-39987 Exploit

Attackers Use LLM Agent for Post-Exploitation After Marimo CVE-2026-39987 Exploit The Hacker News

GoogleMicrosoftLLM AgentMarimoMicrosoft CopilotAI Agents

2 sources: news.google.com, thehackernews.com Updated 16d ago

Low severity STABLE

AI Data Exposure

Fortinet Buys Virtue AI to Hunt Vulnerabilities in AI Agents Before Hackers Do Startup Fortune

AI AgentsData LeakageMCPPrompt InjectionAI Agents BeforeFortinet Buys Virtue

1 source: news.google.com Updated 20d ago