# NebuSec chains a malicious webpage to root access on Meta's Muse agent VM and pulls private chats past its egress gate

The attack used no prompt injection. Separately, a Google DeepMind paper reports that automated agent attackers can still steer models that look robust on public prompt-injection leaderboards.

- Published: 2026-11-22T06:11:42.557Z
- Canonical: https://polylog.news/ai/2026-11-22/nebusec-chains-a-malicious-webpage-to-root-access-on-meta-s
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Meta AI](https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/), [NebuSec](https://nebusec.ai/research/meta-muse-credential-exposure/), [NebuSec](https://nebusec.ai/research/inside-meta-muse/), [Cloud Security Alliance](https://labs.cloudsecurityalliance.org/research/csa-research-note-meta-muse-sentinel-bypass-agent-egress-202/), [arXiv](https://arxiv.org/pdf/2611.11861)

NebuSec, a security research firm, published two write-ups on November 20 describing a full compromise of Muse. Muse is the consumer agent Meta launched on September 8, built on the Muse model line that Meta also sells to developers through…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-11-22/nebusec-chains-a-malicious-webpage-to-root-access-on-meta-s (subscription information: https://polylog.news/pricing).