Microsoft Threat Intelligence has observed threat actors using an agentic AI offensive framework to search public GitHub repositories for exposed secrets, including credentials, application credentials, and AI inference-related API keys across multiple applications and cloud services, which can then be used for further malicious activity against the compromised organization. Searching open code repositories for exposed credentials has historically been limited by the time required for human operators, but agentic tooling like ARTEX allows threat actors to scan for secrets across multiple repositories at a quicker pace and use agents to analyze output and conduct follow-on attacks, cutting down on hands-on-keyboard interactions. In at least one case, Microsoft observed an AI agent advance from scanning GitHub for secrets to exfiltrating data from Azure Key Vault in just five minutes. As early as October 28, 2026, Microsoft began observing successful service principal sign-ins from the IP address 199.19.77[.]84 involving multiple application IDs across some impacted customers, including a multitenant application credential compromised at the source and used to access multiple downstream tenants; the threat actor used the compromised credentials for cloud resource discovery and credential and data exfiltration, including from Azure Key Vaults and Storage Accounts, and abuse of Azure AI services. Microsoft also identified malicious operations from 65.87.223[.]26, including indications of vulnerability exploitation by embedded shell commands in a user agent and attempts to obtain App Service authentication tokens, and observed reconnaissance operations from 157.22.126[.]128