cs.CRNov 9, 2026

Say Shibboleth: Fingerprinting the LLMs and Harnesses Behind Agentic Attacks

Authors: Dario Pasquini, Reworr, Giuseppe Ateniese, Manish Bhatt, Sergej Epp

Organizations: Cracken · Reworr · MATS · George Mason University · 

Abstract

We study the fingerprinting of agentic cyberattacks. Our objective is to reliably infer information about the attacker's configuration, such as LLM version and harness, from telemetry. To achieve this, we introduce a technique we call shibboleth traps: modular honeypot services designed to elicit discriminative behaviors from agentic attackers. The traps make informative interactions a condition for obtaining resources the agent seeks, eliciting model declarations and characteristic writing without requiring a successful prompt injection. To achieve harness fingerprinting, we introduce general mechanisms to indirectly probe peculiar execution behaviors of harnesses. These probes reveal how a harness masks secrets in tool output, enforces command time limits, and schedules tool calls, using only the effects visible in subsequent requests. We show that combined declarative and behavioral inference distinguishes among 15 candidate models with an average 90% top-1 accuracy, with behavioral classifiers evaluated on held-out harnesses or task families. In a separate experiment across four harnesses, fixed probe rules identify the correct harness with 92% accuracy. When instructed to conceal their identity, agents still leave useful behavioral evidence even as their declarations become uninformative.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Sep 23, 2026

Who Is Behind the Harness? Verifying Model Identity in Coding Agents through Behavioral Fingerprinting

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. In coding agents, these signals are mediated by system instructions, controller logic, tools, and execution feedback, limiting their transfer. We present LIDAR (LLM Identification from Decisions and Actions at Runtime), an active black-box fingerprinting method for coding-agent execution. Three coding probe pairs expose post-edit verification, transient-failure recovery, and specification--test conflict resolution under controlled changes. LIDAR represents the resulting trajectories with complementary instance-level and distribution-level features and compares them with clean references using a lightweight probabilistic identifier. It requires no access to model weights, logits, or provider internals. We evaluate 24 models from eight families on OpenCode, OpenHands, and mini-swe-agent, fitting separate references for each harness. Closed-set Top-1 accuracy ranges from 91.39% to 98.89% across the three harnesses, exceeding all three baselines in each setting. When the audit also includes unregistered models from the same families, balanced accuracy ranges from 79.58% to 80.42%. These results show that agent execution behavior provides model-identity evidence beyond final outputs.
May 14, 2026

Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces

As LLM-based agents increasingly browse the web on users' behalf, a natural question arises: can websites passively identify which underlying model powers an agent? Doing so would represent a significant security risk, enabling targeted attacks tailored to known model vulnerabilities. Across 14 frontier LLMs and four web environments spanning information retrieval and shopping tasks, we show that an agent's actions and interaction timings, captured via a passive JavaScript tracker, are sufficient to identify the underlying model with up to 96% F1 within a fixed harness. Although fingerprints are harness-specific, with cross-harness transfer falling to near chance, pooling traces across harnesses recovers model identification at 0.74 to 0.81 Macro-F1. We further show that strong classifiers can be trained from roughly one third of the available traces, and that identification improves steadily as more events are observed. Injecting randomised timing delays between actions substantially degrades classifier performance, but does not provide robust protection: a classifier retrained on delayed traces largely recovers performance. We release our code and a labelled corpus of agent traces at https://github.com/KabakaWilliam/known_actions.
May 10, 2026

AgentShield: Deception-based Compromise Detection for Tool-using LLM Agents

Defenses against indirect prompt injection (IPI) in tool-using LLM agents share two structural weaknesses. First, they all attempt to prevent attacks rather than detect the compromises that slip through. Second, they have only been evaluated in English, leaving users of low-resource languages such as Kurdish and Arabic without tested protection. This paper addresses both gaps with AgentShield, a deception-based detection framework that places three layers of traps inside the agent's tool interface: fake tools, fake credentials, and allowlisted parameters. The same trap triggers serve as high-precision labels for a self-supervised classifier. An LLM agent that follows an attacker's hidden instruction almost always touches one of these traps, which gives both a real-time compromise signal and a zero-FP label for training a downstream detector without manual annotation. Across 176 cross-lingual attack prompts and four LLMs from three providers, and because modern LLMs already refuse most IPI attempts on their own (attack success rate <= 10%), AgentShield's job is to catch the attacks that do slip through. On commercial models, it catches 90.7%-100% of such successful attacks, with zero false alarms on 485 normal-use tests. It survives a systematic adaptive-attack evaluation with zero evasion on commercial models, and the self-supervised classifier transfers across models and languages without retraining.