[KongchangAI]
PersonMohi Uddin

Syed Anas Mohi Uddin

Independent security researcher specializing in AI systems and protocol security. He has identified security vulnerabilities in MCP servers operated by several prominent organizations.

Timeline (last 90 days)

Oct 8

Independent security researcher Syed Anas Mohi Uddin discovered the same security flaw in MCP servers belonging to Google, JPMorgan Chase, and three other organizations: a tool that fetches a given URL without verifying where the address actually points.

Unverified50%
Oct 8

Mohi Uddin described an attack path called protocol pivoting: an attacker plants malicious text in tool output, the first agent passes it to a second agent as a normal task, and the second agent executes it because it trusts the sender.

Unverified50%
Oct 8

The remediation proposed by Mohi Uddin is to check the actual destination of each request and deploy a unified allow list for all tools that fetch URLs, permitting only explicitly trusted destination addresses.

Unverified50%

All Facts (3)

Source Articles