Back to Feed
Threat IntelligenceOct 26, 2026

Forgotten AI agents may still access sensitive company data

Forgotten AI agents retain credentials and connections to company systems, posing security risks.

A report by Arrakis Security reveals that a significant majority of AI agents, approximately 76%, have not run in 60 days, yet still retain credentials and access to sensitive company data. These dormant agents, some with unsecured triggers, can be activated to perform actions, potentially leading to data exfiltration or unauthorized access. The analysis also found that many agents connect to sensitive services without adequate data loss prevention coverage and possess excessive permissions or never-expiring API keys.

AI summary of the linked source. Not reviewed by an editor. How this works

Vendor Watch

Run Arrakis Security?

Get an email when a new story names Arrakis Security, usually within the hour.

Free. Your list stays private and never appears in a subject line. One click stops it. How Vendor Watch worksPrivacy

The lesson from this incident

Full lesson

Organizations are deploying AI agents with broad permissions and long-lived API keys, then forgetting about them — leaving 76% idle for over 60 days while still holding valid credentials to sensitive systems. This 'ghost agent' problem mirrors the classic challenge of orphaned service accounts, but with the added risk of unsecured triggers that allow external actors to reactivate dormant agents and initiate actions like data exfiltration. The lack of data loss prevention coverage over these agent connections compounds the exposure. This matters because attackers increasingly target non-human identities, which are often overlooked in access reviews and lack the same scrutiny as human user accounts.

What helps against this

How we list vendors

Entities

Arrakis Security (vendor)Autonomous Agents (product)AI (technology)OpenAI/Hugging Face incident (campaign)