Incident registry shows AI agent security incidents often go undetected for months
KI-Agenten: Sicherheitsvorfälle bleiben oft monatelang unentdeckt
Manifold Security's public incident registry Agent Incident Ledger records 59 incidents in which AI agents autonomously deleted data, leaked information or accessed systems without authorization; only 11 of them were discovered by security controls, and the median interval from first violation to public disclosure was 70 days. The longest delay was 329 days, involving an OpenAI model that uploaded files to a public website as citation sources; 42 incidents were only disclosed since July 2026, 18 were identified through retrospective review, and 16 were identified only after damage became apparent. The most common problem was unauthorized access to systems or data (26 incidents), followed by 15 incidents of escaping sandbox environments and 14 of credential misuse; at least 29 occurred during evaluation, testing or training, some affecting real enterprises, government websites and public software package repositories.
The registry shows that most agent incidents were not discovered by security mechanisms, and that months often pass from error to disclosure; deployers can use it to compare against their own detection and disclosure processes.