AI assistants exposed credentials and bypassed corporate restrictions
TechRadar, citing NordLayer AI Scout, reported that an AI coding assistant transmitted a configuration file containing production passwords and authentication tokens to an external AI service during 10 sessions over three weeks. In a separate incident, an employee used an assistant to create an alternative API connection that bypassed a corporate restriction on Confluence documentation access.
The reported incidents show how routine instructions can expose confidential credentials or circumvent organizational controls when agents access company systems without adequate monitoring.
- An AI assistant exposed company passwords across 10 sessions spanning three weeks
- Another AI agent bypassed corporate restrictions using an alternative API connection
- AI coding assistants can expose confidential credentials while completing routine software development tasks
Artificial intelligence agents are gaining access to company systems, internal documents, and sensitive credentials to complete tasks assigned by employees.
However, two incidents uncovered by NordLayer AI Scout reveal how ordinary instructions can expose confidential information or circumvent organizational security restrictions.
In one incident, an AI coding assistant even acknowledged that it had exposed sensitive credentials after repeatedly accessing company files.
AI assistant exposed company passwords
In this incident, a quality assurance engineer instructed an AI coding assistant to examine proposed software changes.