paperMay 2026Unreviewed

Oracle Poisoning: Corrupting Knowledge Graphs to Weaponise AI Agent Reasoning

Ben Kereopa-Yorke, Guillermo Diaz, Holly Wright, Reagan Johnston, Ron F. Del Rosario, Timothy Lynar

Abstract

We define Oracle Poisoning, an attack class in which an adversary corrupts a structured knowledge graph that AI agents query at runtime via tool-use protocols, causing incorrect conclusions through correct reasoning. Unlike prompt injection, Oracle Poisoning manipulates the data agents reason over, not their instructions. We demonstrate six attack scenarios against a production 42-million-node code knowledge graph, providing the first empirical demonstration of knowledge graph poisoning against

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection

MITRE ATLAS

AML.T0051LLM Prompt Injection

Suggested from the entry's categories.

Cite

@misc{kereopayorke2026oracle,
  title = {{Oracle Poisoning: Corrupting Knowledge Graphs to Weaponise AI Agent Reasoning}},
  author = {Ben Kereopa-Yorke and Guillermo Diaz and Holly Wright and Reagan Johnston and Ron F. Del Rosario and Timothy Lynar},
  year = {2026},
  month = may,
  eprint = {2605.09822},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.09822}
}