Credential Theft

Credential theft is the unauthorized acquisition of login credentials, authentication tokens, or access keys used to impersonate legitimate users or systems. In AI governance contexts, stolen credentials pose severe risks because they enable attackers to access training data, manipulate model outputs, extract proprietary algorithms, or bypass audit controls. Organizations must implement multi-factor authentication, credential rotation policies, and continuous monitoring to detect compromised accounts before attackers can exploit AI systems or exfiltrate sensitive data.

1 item

ResearchGlobal2026-08-04

Poisoned AI Config Files Turn Sanctioned Coding Agents Into Exfiltration Tools

Security firm Mitiga has documented an attack technique called PromptLogger in which threat actors embed malicious instructions inside AI agent configuration files such as CLAUDE.md and .cursorrules to silently exfiltrate user prompts, credentials, and environment variables. Because the malicious behavior executes through the agent itself, it evades endpoint detection and response tools. The attack directly implicates enterprise AI governance programs that treat sanctioned coding assistants as low-risk approved software.

agentic AI supply chain attack data exfiltration coding assistants prompt injection AI governance credential theft