Add rule for LLM agent indirect prompt injection detection

[Batina-Jennifer]

This Sigma rule detects potential indirect prompt injection manipulation and data exfiltration attempts by monitoring specific command line patterns and parent images in a Linux environment.

Summary of the Pull Request

Changelog

Example Log Event

Fixed Issues

SigmaHQ Rule Creation Conventions

• If your PR adds new rules, please consider following and applying these conventions

[github-actions]

Welcome @Batina-Jennifer 👋

It looks like this is your first pull request on the Sigma rules repository!

Please make sure to read the SigmaHQ conventions to make sure your contribution is adhering to best practices and has all the necessary elements in place for a successful approval.

Thanks again, and welcome to the Sigma community! 😃

If you want to engage more with the community for official support, general discussions or announcements:

👉 Join our Discord server

[nasbench]

Closing this as it looks like AI slop. It also does not adher to the spec nor the conventions defined in the spec repo.
Please refer to the conventions linked above and other rules in the repo.

Also please provide an actual log sample of what you are detecting if you plan to re-open this PR, So that we can easily asses the validity and logic/intent.

Thanks.