APromptRiskDBThreat intelligence atlas
AI Security Technique

Escape to Host - AI Security Technique

Adversaries may break out of a container or virtualized environment to gain access to the underlying host. This can allow an adversary access to other containerized or virtualized resources from the host level or to the host itself. In principle, containerized / virtualized resources should provide a clear separation of application functionality and be isolated from the host environment. There are many ways an adv...

AI Security TechniquedemonstratedPrivilege Escalation

Record summary

A quick snapshot of what this page covers.

Tactics1Attacker goals connected to this method.
Mitigations0Defenses that may help against this attack.
AI risks0Research-backed risks connected to this topic.

Attack context

How this AI attack works in practice.

Adversaries may break out of a container or virtualized environment to gain access to the underlying host. This can allow an adversary access to other containerized or virtualized resources from the host level or to the host itself. In principle, containerized / virtualized resources should provide a clear separation of application functionality and be isolated from the host environment.

There are many ways an adversary may escape from a container or sandbox environment via AI Systems. For example, modifying an AI Agent's configuration to disable safety features or user confirmations could allow the adversary to invoke tools to be run on host environments rather than in the sandbox.

ATLAS ID
AML.T0105
ATT&CK external ID
T1611
Priority score
40
Maturity: demonstrated
Privilege Escalation

Mitigations

Defenses that may help against this attack.

No connected defenses. No defense is connected to this attack in the current data.

Case studies

Examples from public reports and exercises.

OpenClaw 1-Click Remote Code Execution

exercise
Date2026-02-01

A security researcher demonstrated a 1-click remote code execution (RCE) vulnerability to the OpenClaw AI Agent via a malicious link containing a JavaScript script that only takes milliseconds to execute. This vulnerability has been reported and is being tracked to versions of OpenClaw as CVE-2026-25253. [<sup>\[1\]</sup>][1] OpenClaw “is a personal AI assistant you run on your own devices. It answers you on the chat apps you already use. Unlike SaaS assistants where your data lives on someone else’s servers, OpenClaw runs where you choose – laptop, homelab, or VPS. Your infrastructure. Your keys. Your data.” [<sup>\[2\]</sup>][2]

The researcher demonstrated that when the victim clicks a malicious link, a client-side JavaScript script is executed on the victim’s browser that can steal authentication tokens from the OpenClaw control interface via a WebSocket connection. It then uses Cross-Site WebSocket Hijacking to bypass localhost restrictions to the OpenClaw Gateway API. Once the connection was established, it uses the stolen token to authenticate and modify the OpenClaw agent configuration to disable user confirmation and escape the container, allowing shell commands to be run directly on the host machine.

References

  1. [1] https://nvd.nist.gov/vuln/detail/CVE-2026-25253
  2. [2] https://openclaw.ai/blog/introducing-openclaw

LLMSmith: RCE Vulnerabilities in LLM-Integrated Applications

exercise
Date2025-02-27

Researchers identified 20 remote code execution (RCE) vulnerabilities across 11 different LLM frameworks. They discovered applications deployed on the public internet built using these LLM frameworks and demonstrated the RCE vulnerabilities could be exploited using prompt injection.

The 11 LLM frameworks the researchers evaluated were: LangChain, LlamaIndex, Pandas-ai, Langflow, Pandas-llm, Auto-GPT, Griptape, Lagent, MetaGPT, vanna, and langroid.

Source

Where this page information comes from.