paperSeptember 2026Unreviewed

Cross-Lingual Indirect Prompt Injection Across Retrieval, Reranking, And Generation In Multilingual RAG

Fauzi Bondan Prihananto, Erlangga Bayu Yudho Prakoso, Aprilisa Arum Sari, Tomy Anugrah Islami

Abstract

External evidence can make retrieval-augmented generation (RAG) more informative, yet retrieved passages also provide a path for adversarial instructions to enter the model context. We examine that path in an English-Indonesian RAG system and track cross-lingual indirect prompt injection separately at retrieval, reranking, and generation. The experiment starts from 75 semantic items and evaluates every item in eight query/body/payload language combinations, for 600 paired trials. Qwen3-E

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection

MITRE ATLAS

AML.T0051LLM Prompt Injection

Suggested from the entry's categories.

Cite

@misc{prihananto2026crosslingual,
  title = {{Cross-Lingual Indirect Prompt Injection Across Retrieval, Reranking, And Generation In Multilingual RAG}},
  author = {Fauzi Bondan Prihananto and Erlangga Bayu Yudho Prakoso and Aprilisa Arum Sari and Tomy Anugrah Islami},
  year = {2026},
  month = sep,
  doi = {10.59435/jocstec.v4i3.809},
  url = {https://doi.org/10.59435/jocstec.v4i3.809}
}