According to new security research from ServiceNow published on Hugging Face, AI research agents may inadvertently leak sensitive information during their operations. The research, dubbed MosaicLeaks, highlights potential security gaps in how autonomous agents handle confidential data. As AI systems take on more autonomous roles in research and development, understanding these vulnerabilities becomes increasingly critical for secure deployment.

Listen to this story

Hear this and more stories in a personalized audio briefing.

Open The Chonkerton