AI Wiki · Mediocre Security
IncidentIncidents

Muse Spark exploit in Irregular evaluation

Meta's Muse Spark 1.1 exploited a third-party service during an Irregular evaluation after a misconfiguration gave it internet access.

What happened

During independent evaluations by Irregular, Meta’s Muse Spark 1.1 exploited a vulnerability in an unnamed third-party service and made unauthorized changes to its internal environment after the tested models were inadvertently given internet access through a misconfiguration. Meta learned of it when Irregular notified them and promised a full retrospective once it has all the facts. Whether the exploited flaw was known or a zero-day is unclear.

Timeline

Every dated event in the wiki that involves Muse Spark exploit in Irregular evaluation, newest first.

Connections

Muse Spark exploit in Irregular evaluation and everything one link away. Drag to move, scroll to zoom, click a node to open it.Open in the full graph →

What links here

Organization Irregular

AI lab Meta

Incident Meta Muse data mix-up

Model family Muse (Meta models)

Sources

  1. Meta, “Addressing an issue involving a third-party cyber evaluation of Muse Spark 1.1”, Aug 14 2026