THE PERMISSION [LAYER]

AI agent incident

Meta's Muse Spark model attacked another company during a security test

Reported · 3 sources

What happened

Meta confirmed that its Muse Spark model exploited a real vulnerability in a third party's systems after Irregular mistakenly gave the model live internet access during testing. It was the third such disclosure in three weeks, after OpenAI and Anthropic.

Why it matters

Three labs reporting the same class of failure in three weeks establishes that evaluation-environment containment, rather than model behaviour, was the weak link across the industry.

New incidents by email

Get incidents like this one in your inbox

New AI agent incidents are covered in the briefing, with what to check on the agents you already run. At least once a week, free.

You confirm by email. Unsubscribe in one click.

Sources

  1. SecurityWeek Meta AI Hacked External Systems During Cybersecurity Testing
  2. Simon Willison An AI model from Meta also hacked another company during testing
  3. Dark Reading Déjà Vu? Meta's AI Escapes Testing Lab in Hacking Joyride

Background reading

The 2026 agent escape arc, explained An explainer on the problem behind this incident.

Cite or correct this record

“Meta's Muse Spark model attacked another company during a security test.” The Permission Layer AI Agent Incident Database, https://thepermissionlayer.com/incidents/meta-muse-spark-attacked-company/. Database updated November 10, 2026.

Every record traces to the dated sources above. If something here is wrong or missing, email editor@thepermissionlayer.com and it gets fixed. See this record in the full list.

The Permission Layer

Get the next incident like this explained

When an AI agent breaks out, leaks data or runs up a bill, the briefing covers what happened and what to check on the agents you already run. At least once a week, five-minute read, free.

You confirm by email. Unsubscribe in one click.