Who Is Behind the Harness? Fingerprinting LLMs through Agentic Behavior

Reported by arXiv cs.CR (Chuyi Wang, Xiaohui Xie, Tongze Wang, Fangchen Luo, Yong Cui)

Summary by Cyber Security News25 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/2609.28559

arXiv:2609.28559v1 Announce Type: new Abstract: LLMs increasingly operate through coding-agent harnesses that inspect repositories, invoke tools, and modify files. Substituting the model behind such an agent can therefore change security-relevant decisions, including whether it verifies changes or recovers safely from failures. Existing LLM fingerprints largely infer identity from direct text or token distributions.

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

SECURITY AFFAIRS AI-CYBERSECURITY NEWSLETTER ROUND 1

Security Affairs newsletter Round 597 by Pierluigi Paganini – INTERNATIONAL EDITION

Secure AI Adoption: Close the Governance Gap to Accelerate AI in the Cloud

From Opus 5 to Opus 5.5: better fixes at 58% less cost in the SonarQube Remediation Agent

AI-Powered CARBONATO Botnet Steals Credentials to Fund Its Own LLM Gateway

Privacy Leakage Through AI-mediated Analysis of Smartphone Data