KidnapRAG: A Black-Box Attack for Hijacking Reasoning in Agentic Retrieval-Augmented Generation Systems

[2607.00422] KidnapRAG: A Black-Box Attack for Hijacking Reasoning in Agentic Retrieval-Augmented Generation Systems Skip to main content Search Submit Donate Log in Computer Science > Cryptography and Security arXiv:2607.00422 (cs) [Submitted on 1 Jul 2026 ( v1 ), last revised 28 Aug 2026 (this version, v2)] Title: KidnapRAG: A Black-Box Attack for Hijacking Reasoning in Agentic Retrieval-Augmented Generation Systems Authors: Chanwoo Choi , Euntae Kim , Kyuho Lee , Youngsam Chun , Jinhee Jeong , Eunmi Kim , Myunggyo Oh , Junseo Jang , Buru Chang View PDF HTML (experimental) Abstract: Retrieval-Augmented Generation (RAG) systems are vulnerable to poisoning attacks that inject malicious documents into the retrieval process to manipulate model outputs. Recent Agentic RAG systems are more robust to such attacks because they iteratively perform retrieval and reasoning, allowing them to ignore weakly relevant poisoned documents and preserve the reasoning chain induced by the user query. However, existing attacks on Agentic RAG systems often assume white-box access to system prompts, reasoning traces, retrievers, or model parameters, limiting their applicability in realistic settings. In this paper, we study black-box poisoning attacks against Agentic RAG systems, where the attacker can only publish externally retrievable poisoned documents. We propose KidnapRAG, a sequential poisoning attack that hijacks the agent's multi-step reasoning chain using three role-specific documents: Bait, Chain-Link, and Mal-Ins, which attract initial retrieval, induce query reformulation, and provide attacker-controlled evidence, respectively. Experiments across multiple Agentic RAG frameworks, LLM backbones, and benchmarks show that KidnapRAG consistently outperforms existing poisoning baselines under black-box conditions. Further analyses show that KidnapRAG progressively weakens the original retrieval intent, redirects retrieval behavior, and increases reliance on attacker-controlled evidence. Our code is publicly available at this https URL . Comments: Accepted to the Main Conference of EMNLP 2026 Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2607.00422 [cs.CR] (or arXiv:2607.00422v2 [cs.CR] for this version) https://doi.org/10.48550/arXiv.2607.00422 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Chanwoo Choi [ view email ] [v1] Wed, 1 Jul 2026 04:32:17 UTC (1,538 KB) [v2] Fri, 28 Aug 2026 04:35:25 UTC (1,543 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.CR < prev | next > new | recent | 2026-07 Change to browse by: cs References & Citations SciX 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 Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from (opens in new tab) (opens in new tab) (opens in new tab)

Related documents

• KidnapRAG: A Black-Box Attack for Hijacking Reasoning in Agentic Retrieval-Augmented Generation Systems#682742
• KidnapRAG: A Black-Box Attack for Hijacking Reasoning in Agentic Retrieval-Augmented Generation Systems#329032
• ToxicRAG: Compromising Retrieval-Augmented Generation Systems via Single-Shot Knowledge Poisoning Attacks#673418
• RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations#229581
• Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory#1064897