vulnerability
Google Dialogflow CX Bug Allowed Attackers to Hijack AI Conversations
High
Summary
A vulnerability in Google Cloud’s Dialogflow CX service allowed attackers to silently control agents, manipulate conversations, and exfiltrate sensitive information. The flaw stemmed from a permissive configuration within the Cloud Run execution environment, enabling attackers to inject malicious code and bypass security controls. Google released a patch in June 2025 after reporting the vulnerability in November 2025.
Summary written automatically in our own words from the original article, which belongs to its publisher and remains the reference. It may contain errors. Sources & data