Foundations for Agentic AI Investigations from the Forensic Analysis of OpenClaw
This addresses the need for systematic forensic approaches in agentic AI, which is incremental as it provides an initial foundation for digital investigations in this emerging domain.
This paper tackles the problem of reconstructing the internal state and actions of agentic AI systems during forensic analysis by empirically studying OpenClaw, a widely used single-agent assistant, through static code analysis and differential forensic analysis to classify recoverable traces and propose an agent artifact taxonomy.
Agentic Al systems are increasingly deployed as personal assistants and are likely to become a common object of digital investigations. However, little is known about how their internal state and actions can be reconstructed during forensic analysis. Despite growing popularity, systematic forensic approaches for such systems remain largely unexplored. This paper presents an empirical study of OpenClaw a widely used single-agent assistant. We examine OpenClaw's technical design via static code analysis and apply differential forensic analysis to identify recoverable traces across stages of the agent interaction loop. We classify and correlate these traces to assess their investigative value in a systematic way. Based on these observations, we propose an agent artifact taxonomy that captures recurring investigative patterns. Finally, we highlight a foundational challenge for agentic Al forensics: agent-mediated execution introduces an additional layer of abstraction and substantial nondeterminism in trace generation. The large language model (LLM), the execution environment, and the evolving context can influence tool choice and state transitions in ways that are largely absent from rule-based software. Overall, our results provide an initial foundation for the systematic investigation of agentic Al and outline implications for digital forensic practice and future research.