> [!NOTE]
> Premium and Enterprise (Deprecated) [service tiers](https://docs.cloud.google.com/security-command-center/docs/service-tiers.md.txt)

> [!CAUTION]
> The Security Command Center Enterprise service tier will shut down on May 21, 2027. If your organization uses the Enterprise service tier, then the organization will automatically move to the Premium service tier on or after May 21, 2027. Contact your account representative or a [Google Cloud sales specialist](https://cloud.google.com/contact) if you have questions.

This document describes a threat finding type in Security Command Center. Threat findings are generated by
[threat detectors](https://docs.cloud.google.com/security-command-center/docs/concepts-security-sources.md.txt#threats) when they detect
a potential threat in your cloud resources. For a full list of available threat findings, see [Threat findings index](https://docs.cloud.google.com/security-command-center/docs/threat-findings-index.md.txt).

## Overview

A process was detected launching a code compiler tool within an AI agent
environment. This behavior suggests a potential attempt to develop or compile
malicious software within the isolated AI agent, possibly to obfuscate malicious
activities and evade traditional host-based security controls. Adversaries might
utilize this technique to create custom tools or modify existing binaries in a
less scrutinized environment before deploying them to the underlying system or
other targets. The presence of a code compiler within an AI agent, especially if
unexpected, warrants investigation as it could indicate an attacker preparing to
introduce persistent backdoors or compromise client software through tampered
binaries.

[Agent Platform Threat Detection](https://docs.cloud.google.com/security-command-center/docs/agent-engine-threat-detection-overview) is the
source of this finding.

## How to respond

To respond to this finding, do the following:

### Review finding details

1. Open the `Defense Evasion: Launch Code Compiler Tool In Container` finding as directed
   in [Reviewing
   findings](https://docs.cloud.google.com/security-command-center/docs/how-to-investigate-threats#reviewing_findings).
   Review the details on the **Summary** and **JSON** tabs.

2. On the **Summary** tab, review the information in the following sections:

   - **What was detected** , especially the following fields:
     - **Program binary**: the absolute path of the executed binary
     - **Arguments**: the arguments passed during binary execution
   - **Affected resource** , especially the following fields:
     - **Resource full name** : the [full resource
       name](https://docs.cloud.google.com/apis/design/resource_names) of the affected Agent Runtime resource
3. On the **JSON** tab, note the following fields.

   - `resource`:
     - `project_display_name`: the name of the project that contains the cluster.
   - `finding`:
     - `processes`:
     - `binary`:
       - `path`: the full path of the executed binary.
     - `args`: the arguments that were provided while executing the binary.
4. Identify other findings that occurred at a similar time for this AI agent.
   Related findings might indicate that this activity was malicious, instead of
   a failure to follow best practices.

5. Review the settings of the affected AI agent.

6. Check the logs for the affected AI agent.

### Research attack and response methods

1. Review MITRE ATT\&CK framework entry for this finding type: [Obfuscated Files or Information: Compile After Delivery](https://attack.mitre.org/techniques//T1027/004/).
2. To develop a response plan, combine your investigation results with MITRE research.

### Implement your response

For response recommendations, see [Respond to Agent Runtime threat
findings](https://docs.cloud.google.com/security-command-center/docs/respond-ai-threats).

## What's next

- Learn [how to work with threat
  findings in Security Command Center](https://docs.cloud.google.com/security-command-center/docs/how-to-investigate-threats).
- Refer to the [Threat findings index](https://docs.cloud.google.com/security-command-center/docs/threat-findings-index.md.txt).
- Learn how to [review a
  finding](https://docs.cloud.google.com/security-command-center/docs/how-to-investigate-threats#reviewing_findings) through the Google Cloud console.
- Learn about the [services that
  generate threat findings](https://docs.cloud.google.com/security-command-center/docs/concepts-security-sources#threats).