Critical Vulnerability in GCP Dialogflow Allows Attackers to Inject Malicious Code

Cybersecuritynews •Guru Baran • July 7, 2026

A critical vulnerability in Google Cloud Platform’s Dialogflow CX that lets attackers inject persistent malicious code into an organization’s AI-powered chatbot pipeline. The flaw, dubbed “Rogue Agent,” disclosed by Varonis Threat Labs, could silently exfiltrate conversations and enable large-scale phishing campaigns, requiring only a single edit permission to trigger. The exploit abused Playbook Code Blocks, […]

The full story

This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.

Critical Rogue Agent Vulnerability in GCP Dialogflow Exposes Chatbots to Attacks A critical vulnerability, named 'Rogue Agent', has been discovered in Google Cloud Platform's Dialogflow CX, allowing attackers to inject persistent malicious code into AI chatbots. This flaw, reported by Varonis Threat Labs, requires only a single edit permission to exploit. Attackers can exfiltrate conversations and potentially launch large-scale phishing campaigns. The vulnerability affects organizations using Dialogflow CX, posing a significant risk to their chatbot operations. No specific CVE has been assigned yet, and the current status of the vulnerability is under investigation. Security professionals are urged to review permissions and access controls to mitigate risks. 5 sources 71

Extracted Entities

Critical Vulnerability in GCP Dialogflow Allows Attackers to Inject Malicious Code

The full story

Extracted Entities

Attack Types (1)

Companies (1)

CWE Weaknesses (2)

MITRE ATT&CK (2)

Platforms (1)

Vulnerabilities (1)