Home Technology Millions of AI agents imperiled by critical...
Technology

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

Key Points

A critical vulnerability has been discovered in Starlette, a widely used open-source framework that receives 325 million weekly downloads. This flaw could allow hackers to breach servers running AI agents, potentially stealing sensitive data and credentials stored by Model Context Protocol (MCP) servers. Thousands of other open-source projects relying on Starlette are also affected by this easily exploitable security risk.

Millions of AI agents and tools around the world have been imperiled by a critical vulnerability that can allow hackers to breach the servers running them and make off with sensitive data and credentials to third-party accounts, a security researcher is warning.

The vulnerability is present in Starlette, an open source framework that its developer says receives 325 million downloads per week. Thousands of other open source projects are also vulnerable because they require Starlette to work. The framework is an implementation of the ASGI (asynchronous server gateway interface), which allows large numbers of requests to be efficiently processed simultaneously. Starlette is the base of FastAPI and other widely used frameworks for building services in Python apps, as well as many others.

Trivial to exploit, millions of servers exposed

ASGI, and by extension Starlette, have access to servers running the MCP (model context protocol), which allows AI agents from major providers to access external sources, including user data bases, email and calendar accounts, and all manner of other resources. To connect with these external systems, MCP servers store credentials for each one, making them especially valuable storehouses for attackers to breach.

Read full article

Comments

Originally published by Ars Technica Read original →