paperJuly 2026Unreviewed

Just Testing, Move Along: Evasion of LLM-based System Log Interpretation by Prompt Injection

Max Landauer, Florian Skopik, Markus Wurzenberger, Franciszek Górski, Mateusz Krzysztoń

Abstract

Large Language Models (LLMs) are increasingly integrated into Security Operations Center (SOC) workflows, where they support analysts in tasks such as the interpretation of system logs. However, the ability of LLMs to directly process untrusted textual input also introduces new attack surfaces. In particular, attackers can inject contextual information or explicit instructions into log entries in order to influence how malicious activity is interpreted by the model. Despite the growing adoption

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection

MITRE ATLAS

AML.T0051LLM Prompt Injection

Suggested from the entry's categories.

Cite

@misc{landauer2026just,
  title = {{Just Testing, Move Along: Evasion of LLM-based System Log Interpretation by Prompt Injection}},
  author = {Max Landauer and Florian Skopik and Markus Wurzenberger and Franciszek Górski and Mateusz Krzysztoń},
  year = {2026},
  month = jul,
  eprint = {2607.24174},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.24174}
}