From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors

Computer Science > Cryptography and Security [Submitted on 29 May 2026] From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors Jiejun Tan, Zhicheng Dou, Xinyu Yang, Yuyang Hu, Yiruo Cheng, Xiaoxi Li, Ji-Rong Wen LLM agents are evolving from conversational chatbots to operational tools in real-world workspaces. In local agentic harnesses, an LLM can read and write files, call tools, and reuse workspace state across sessions. While such capabilities enhance utility, they also expose a new attack surface for attackers. Attackers can embed a prompt injection within a file or tool output. Agents may read this hidden instruction, store it, and execute it later. In this multi-step trojan attack paradigm, no individual step appears malicious on its own, but these steps can collectively turn untrusted text into persistent control content. However, existing defenses often inspect each step in isolation. As a result, they can block a clear harmful action, but fail to detect the earlier write operation that plants the backdoor. To reveal this threat, we introduce ClawTrojan, a benchmark designed to identify multi-step trojan attacks in local agentic harnesses. In an OpenClaw-style simulated workspace with GPT-5.4, ClawTrojan reaches a 95.5% attack success rate (ASR), while existing single-turn prompt-injection attacks produce near-zero ASR on the same model. To address this threat, we propose DASGuard, which scans control-like text in sensitive local files, traces its origin, and removes control content that does not originate from a trusted source. Our results show that DASGuard achieves strong dynamic defense by combining runtime attack blocking with sanitized commits to the workspace. Comments: Code and data are available at this https URL Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) Cite as: arXiv:2605.31042 [cs.CR]   (or arXiv:2605.31042v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2605.31042 Focus to learn more Submission history From: Jiejun Tan [view email] [v1] Fri, 29 May 2026 09:19:07 UTC (3,857 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-05 Change to browse by: cs cs.AI cs.CL References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)