Hearsay: Can an Auditor Trust the Record a Deployed Agent Harness Writes?

Reported by arXiv cs.CR (Jiahong Dai, Zhuochen Yang, Pengyang Shao, Kelvin Ng, Zhongyi Liu, Chengquan Ju, Yuting He, Bo Hu)

Summary by Cyber Security News29 Sep 2026, 06:00 CEST

About this summary. This is a short, independently written summary of an article first published by arXiv cs.CR. Cyber Security News did not report or verify the underlying story. Read the original: https://arxiv.org/abs/2609.32495

arXiv:2609.32495v1 Announce Type: new Abstract: An agent harness, the code that turns a model into an agent, writes its own record of each run, and that record is all a later reader gets when a run is disputed, investigated or audited. We call a record evidentiary when a reader who was not there can check it without trusting the writer. Across sixteen deployed frameworks, none writes one in full.

Read the full article at arXiv cs.CR →

Source attribution: headline and facts are from arXiv cs.CR (arxiv.org). Summary method: excerpt of the source description. See our source attribution policy.

Related coverage

A Large-Scale Benchmark and Risk Assessment of Traffic Analysis Attacks on Cloud LLM Services

BMA: Backchain Memory Attacks Create Unauthorized Control Paths in LLM Agents

CyberClear: A Benchmark for LLM Agent Systems on APT Attack Chain Provenance

REFINE: A Resilient Evolution Framework for Intelligent Enterprise Alert Triage in Security Operations Centers

Trust the Brand, Lose Control: How Identity Hijacks LLM Agent Orchestration

Ask Without Telling: Local SLMs Consult Cloud LLMs Without Revealing Task Intent