Navigation
Recherche
|
MCP attack abuses predictable session IDs to hijack AI agents
mardi 21 octobre 2025, 21:36 , par TheRegister
The vuln affects the Oat++ MCP implementation
A security flaw in the Oat++ implementation of Anthropic's Model Context Protocol (MCP) allows attackers to predict or capture session IDs from active AI conversations, hijack MCP sessions, and inject malicious responses via the oatpp-mcp server.…
https://go.theregister.com/feed/www.theregister.com/2025/10/21/mcp_prompt_hijacking_attack/
Voir aussi |
56 sources (32 en français)
Date Actuelle
mer. 22 oct. - 07:13 CEST
|