ServiceNow Now Assist default settings reportedly open door to prompt injection attacks
Reports say default configurations of ServiceNow's AI assistants can be exploited for prompt injection attacks. The news dates from 19 November 2025.
Who is affected and how
- security leader
- The permissions of agentic features should be risk-assessed before deployment.
- security operations
- Default settings of AI assistants should be reviewed and tightened.
Sources
- Hackers Can Exploit Default ServiceNow AI Assistants Configurations to Launch Prompt Injection Attackscyber press · Nov 19, 2025
- Malicious actors can exploit default configurations in ServiceNow's Now Assist generative artificial intelligence (AI) platform and leverage its agentic capabilities to conduct prompt injection attacks. | Arthur deAlbalinkedin.com · Nov 19, 2025
- Cybersecurity Threats in Agentic Artificial Intelligence Developmnatlawreview.com · Nov 21, 2025
Machine-generated summary based on the titles and excerpts of the source articles. The facts come from the linked article. News monitoring and analysis, not security advice. Attributions belong to those who made them.
What do you make of this piece?
The split shows after 20 votes.
Why? Your answer is not shown publicly; it helps the editors.