AgentForensics: Exploring the Real-Time Prompt Injection Detection and Forensics Threats in LLM Agents

Abstract

With LLM agents increasingly deployed to autonomously processed external content like web pages, emails, documents, and API responses become targets of indirect prompt injection attacks where malicious instructions embedded in external content hijack the agent's behavior. Existing defenses focus primarily on filtering user-layer inputs, leaving the wider attack surface unaddressed. In this paper, we present AgentForensics, an open-source security framework that monitors entire LLM agent sessions

Categories

Framework mappings

Suggested from the entry's categories.

@misc{arulljothi2026agentforensics,
  title = {{AgentForensics: Exploring the Real-Time Prompt Injection Detection and Forensics Threats in LLM Agents}},
  author = {Aparnaa Mahalaxmi Arulljothi and Theepan Kumar Gandhi},
  year = {2026},
  doi = {10.2139/ssrn.6589479},
  url = {https://doi.org/10.2139/ssrn.6589479}
}