Threat Actor Reportedly Used LLM Agent to Exfiltrate Internal Database After Compromising marimo Python Notebook

May 10, 2026

An unidentified attacker reportedly used an LLM agent during a May 10 intrusion after exploiting a vulnerable marimo Python notebook. The agent reportedly reused harvested AWS credentials to obtain an SSH key, then pivoted through a bastion host and exfiltrated the schema and contents of an internal PostgreSQL database. Sysdig attributed the post-compromise command stream to real-time agent execution rather than a prebuilt script. …contributors—JOIN US—to learn more.

Matched TAIM controls

Suggested mapping from embedding similarity (not a formal assessment). Browse all TAIM controls

MEASURE 1.3 — similarity 0.581, rank 1. TAIM detail and related incidents →
GOVERN 6.1 — similarity 0.578, rank 2. TAIM detail and related incidents →
MANAGE 2.3 — similarity 0.574, rank 3. TAIM detail and related incidents →

Alleged deployer: threat-actors, hackers, cybercriminals, ai-agent-system-deployers, agentic-threat-actors
Alleged developer: large-language-model-developers, ai-agent-system-developers
Alleged harmed parties: victims-of-automated-cybercrime, enterprise-it-systems, amazon-web-services-(aws)-customers, information-security, privacy

AI governance case studies

For forensic AI governance failure analysis (TAIMScore™ case studies), browse Human Signal’s Failure Files™.

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/1670

Data source

Incident data is from the AI Incident Database (AIID).

When citing the database as a whole, please use:

McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. In Proceedings of the Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-21). Virtual Conference.

Pre-print on arXiv · Database snapshots & citation guide

We use weekly snapshots of the AIID for stable reference. For the official suggested citation of a specific incident, use the “Cite this incident” link on each incident page.