Skip to content
Search
paperJune 2026Unreviewed

GitInject: Real-World Prompt Injection Attacks in AI-Powered CI/CD Pipelines

Jafar Isbarov, Umid Suleymanov, Ilia Shumailov, Murat Kantarcioglu

View resourcePDF

Abstract

AI-powered agents are increasingly embedded in continuous integration and continuous delivery/deployment (CI/CD) pipelines to autonomously review pull requests (PRs), triage issues, and maintain codebases. These agents ingest untrusted content while operating with elevated repository permissions, making them a natural target for prompt injection attacks with supply chain consequences. We present GitInject, an open-source framework for evaluating prompt injection vulnerabilities in real, live Git

Categories

Prompt InjectionSupply Chain Attacks

Framework mappings

OWASP Top 10 for LLM Applications
  • LLM01Prompt Injection
  • LLM03Supply Chain
MITRE ATLAS
  • AML.T0010AI Supply Chain Compromise
  • AML.T0051LLM Prompt Injection

Suggested from the entry's categories.

Cite

@misc{isbarov2026gitinject,
  title = {{GitInject: Real-World Prompt Injection Attacks in AI-Powered CI/CD Pipelines}},
  author = {Jafar Isbarov and Umid Suleymanov and Ilia Shumailov and Murat Kantarcioglu},
  year = {2026},
  month = jun,
  eprint = {2606.09935},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.09935}
}