paperJuly 2026Unreviewed

Context Contamination in LLM Analysis of Network Security Logs: Poison with Passive Prompt Injection and Mitigation Evaluation

Rabimba Karanjai, Yang Lu, Hemanth Hegadehalli Madhavarao, Lei Xu, Weidong Shi

Abstract

Large Language Models are increasingly deployed in Security Operations Centers for log analysis tasks including summarization, alert triage, and threat investigation. These systems ingest logs from external-facing services and process network logs as natural language contexts to generate security insights. We demonstrate that this architectural pattern introduces a critical vulnerability: adversaries can embed prompt injection payloads in log-generating fields that persist in storage and are exe

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection

MITRE ATLAS

AML.T0051LLM Prompt Injection

Suggested from the entry's categories.

Cite

@misc{karanjai2026context,
  title = {{Context Contamination in LLM Analysis of Network Security Logs: Poison with Passive Prompt Injection and Mitigation Evaluation}},
  author = {Rabimba Karanjai and Yang Lu and Hemanth Hegadehalli Madhavarao and Lei Xu and Weidong Shi},
  year = {2026},
  month = jul,
  eprint = {2607.14493},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.14493}
}