Malicious Email Could Hijack AI Agent and Access Connected Accounts

Salt Labs, the research arm of Salt Security, discovered a now-fixed vulnerability in agentic AI platform Manus that let a single malicious email hijack an AI agent and potentially reach a user's connected accounts, because Manus interpreted instructions embedded in incoming messages. The flaw has been remediated, according to the researchers' disclosure.

Security researchers have uncovered a now-fixed vulnerability in agentic AI platform Manus that could have allowed attackers to hijack an AI agent through a single malicious email and potentially access a user’s connected accounts. Researchers at Salt Labs, the research arm of Salt Security, found that Manus could interpret malicious instructions embedded within an incoming … The post Malicious Email Could Hijack AI Agent and Access Connected Accounts https://www.itsecurityguru.org/2026/10/02/malicious-email-could-hijack-ai-agent-and-access-connected-accounts/ appeared first on IT Security Guru https://www.itsecurityguru.org .