When AI Escapes the Lab:
The Hugging Face Breach, PyPI Malware, and What It Means for Defenders

Fully autonomous attacks are here. AI agents escape a test environment, exploit zero-days, coordinate through shared infrastructure, and breach a production company—generating more than 17,000 security events along the way. Elsewhere, another model autonomously publishes malware to PyPI, while AI agents target real open-source developers with tailored social engineering.

Join hosts John Dilgen and Tehman Tariq as they break down:

• How AI agents escaped containment and compromised Hugging Face infrastructure
• Why Claude’s autonomous PyPI attack signals growing software-supply-chain risk
• How coordinated AI agents deceived real developers

Two questions your organization should be asking right now:

• Could your SOC investigate and contain 17,000 coordinated events at machine speed?
• What deception controls do you have in place to slow an AI agent attack?

Resources: https://linktr.ee/ReliaQuestShadowTalk

John Dilgen: Cyber Threat Intelligence Analyst at ReliaQuest, where he specializes in researching cyber threats impacting ReliaQuest customers. With a strong technical background, he previously served as an Incident Response Analyst and Trainer at ReliaQuest.

Tehman Tariq: Sr. Manager of Cyber Operations at ReliaQuest, where he has spent a majority of his career leading Incident Response, Security Architecture, and Detection teams. He has worked hand in hand with CISOs to introduce automation that allows teams to mature their security programs.