# k8sGPT has Prompt Injection through its k8sGPT-Operator

Source: https://junglewise.ai/threats/k8sgpt-has-prompt-injection-through-its-k8sgpt-operator-3b2134dd  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-04-24. Updated: 2026-05-11  
License: CC BY 4.0 with a link back

Severity: high · Published 2026-04-24

### Summary
In the auto-remediation pipeline, `object_to_execution.go` was deserializing the AI-generated YAML directly into a Deployment object, but there was lack of validation from the original Deployment object.

### Details
This issue was fixed after coordination with Alex Jones.

### PoC
To minimize the impact, the PoC of this vulnerability wasn't released, but was shared with the maintainers.

Technologies: [github.com/k8sgpt-ai/k8sgpt (Go)](https://junglewise.ai/threats/technologies/github-com-k8sgpt-ai-k8sgpt). Vendors: [Go](https://junglewise.ai/threats/vendors/go).

## Quick answers

**Is This vulnerability exploited in the wild?** No. Junglewise Threat Intelligence has no report of This vulnerability being exploited in the wild.

**How severe is This vulnerability?** High severity, published 24 April 2026.

**Which products and versions are affected?** github.com/k8sgpt-ai/k8sgpt (Go) < 0.4.32.

**Is there a fix for This vulnerability?** No fixed version is recorded yet. Check the vendor's advisory in the references below. If you run it, Junglewise drafts a mitigation that fits your setup and applies it once you approve, with senior security engineers behind it.

**Am I affected?** Check whether you run github.com/k8sgpt-ai/k8sgpt (Go) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## Affected products

- github.com/k8sgpt-ai/k8sgpt (Go) < 0.4.32

## References

- [https://api.github.com/users/haruki3hhh](https://api.github.com/users/haruki3hhh)
- [https://github.com/haruki3hhh](https://github.com/haruki3hhh)
- [https://api.github.com/users/haruki3hhh/gists%7B/gist_id%7D](https://api.github.com/users/haruki3hhh/gists%7B/gist_id%7D)
- [https://api.github.com/users/haruki3hhh/repos](https://api.github.com/users/haruki3hhh/repos)
- [https://avatars.githubusercontent.com/u/135201297?v=4](https://avatars.githubusercontent.com/u/135201297?v=4)
- [https://api.github.com/users/haruki3hhh/events%7B/privacy%7D](https://api.github.com/users/haruki3hhh/events%7B/privacy%7D)

## Related threats

- [GO-2026-5631 - k8sGPT has Prompt Injection through its k8sGPT-Operator in github.com/k8sgpt-ai/k8sgpt](https://junglewise.ai/threats/go-2026-5631-k8sgpt-has-prompt-injection-through-its-k8sgpt-operator-in-bc838edf)
- [GO-2024-2923 - Vulnerabilities with the k8sGPT in github.com/k8sgpt-ai/k8sgpt](https://junglewise.ai/threats/go-2024-2923-vulnerabilities-with-the-k8sgpt-in-github-com-k8sgpt-ai-b2fd0f03)
- [Vulnerabilities with the k8sGPT](https://junglewise.ai/threats/vulnerabilities-with-the-k8sgpt-430aebe1)