Three vulnerabilities in Anthropic’s MCP Git server allow prompt injection attacks that can read or delete files and, in some ...

Available in a technical preview, the SDK for Node.js, Python, Go, and .NET provides programmatic access to the agentic power ...

Security researchers uncovered two vulnerabilities in the popular Python-based AI app building tool that could allow ...

Here's what happened next ...

High-severity flaws in the Chainlit AI framework could allow attackers to steal files, leak API keys & perform SSRF attacks; ...

Researchers with Cyata and BlueRock uncovered vulnerabilities in MCP servers from Anthropic and Microsoft, feeding ongoing security worries about MCP and other agentic AI tools and their dual natures ...

The attack consists of a NexShield malicious browser extension, a social engineering technique to crash the browser, and a ...

A coordinated campaign has been observed targeting a recently disclosed critical-severity vulnerability that has been present ...

Update Chainlit to the latest version ASAP Two "easy-to-exploit" vulnerabilities in the popular open-source AI framework ...

Vulnerabilities in Chainlit could be exploited without user interaction to exfiltrate environment variables, credentials, ...

ClickFix variant CrashFix relies on a malicious Chrome extension to crash the browser and trick victims into installing the ...

I tried four vibe-coding tools, including Cursor and Replit, with no coding background. Here's what worked (and what didn't).