> [!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.


> [!WARNING]
>
> **Preview**
>
>
> This feature is
>
> subject to the "Pre-GA Offerings Terms" in the General Service Terms section of the
> [Service Specific
> Terms](https://docs.cloud.google.com/terms/service-terms#1).
>
> Pre-GA features are available "as is" and might have limited support.
>
> For more information, see the
> [launch stage descriptions](https://cloud.google.com/products/#product-launch-stages).

<br />

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 loaded a library that is included in the original agentic workload.
The library was modified at runtime and was identified as malicious based on
threat intelligence.

Attackers might load malicious libraries into existing programs to
bypass code execution protections and to hide malicious code.

[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 `Execution: Modified Malicious Library Loaded` 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 full path of the process binary that loaded the library
     - **Libraries**: details about the modified library
     - **Arguments**: the arguments provided when invoking the process binary
   - **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 AI agent (a [`ReasoningEngine`](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/reference/rest/v1/projects.locations.reasoningEngines#ReasoningEngine) resource)
   - **Related links** , especially the following fields:
     - **VirusTotal indicator**: link to the VirusTotal analysis page
3. Look for related findings that occurred at a similar time for the affected
   AI agent. Such findings might indicate that this activity was malicious,
   instead of a failure to follow best practices.

4. Review the settings of the affected AI agent.

5. Check the logs for the affected AI agent.

### Research attack and response methods

1. Review the MITRE ATT\&CK framework entries for this finding type: [Ingress Tool Transfer](https://attack.mitre.org/techniques/T1105/) and [Shared Modules](https://attack.mitre.org/techniques/T1129/).
2. Check the SHA-256 hash value for the binary flagged as malicious on [VirusTotal](https://www.virustotal.com) by clicking the link in **VirusTotal indicator**. VirusTotal is an Alphabet-owned service that provides context on potentially malicious files, URLs, domains, and IP addresses.
3. To develop a response plan, combine your investigation results with the MITRE research and VirusTotal analysis.

### Implement your response


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

<br />

## 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).