Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systems

• URL: http://arxiv.org/abs/2601.07072v1
• Date: Sun, 11 Jan 2026 21:33:59 GMT
• Title: Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systems
• Authors: Hongyan Chang, Ergute Bao, Xinjian Luo, Ting Yu,
• Abstract summary: Large language models (LLMs) increasingly rely on retrieving information from external corpora.<n>This creates a new attack surface: indirect prompt injection (IPI)<n>We present the first end-to-end IPI exploits under natural queries and realistic external corpora.
• Score: 7.15710884787427
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) increasingly rely on retrieving information from external corpora. This creates a new attack surface: indirect prompt injection (IPI), where hidden instructions are planted in the corpora and hijack model behavior once retrieved. Previous studies have highlighted this risk but often avoid the hardest step: ensuring that malicious content is actually retrieved. In practice, unoptimized IPI is rarely retrieved under natural queries, which leaves its real-world impact unclear. We address this challenge by decomposing the malicious content into a trigger fragment that guarantees retrieval and an attack fragment that encodes arbitrary attack objectives. Based on this idea, we design an efficient and effective black-box attack algorithm that constructs a compact trigger fragment to guarantee retrieval for any attack fragment. Our attack requires only API access to embedding models, is cost-efficient (as little as $0.21 per target user query on OpenAI's embedding models), and achieves near-100% retrieval across 11 benchmarks and 8 embedding models (including both open-source models and proprietary services). Based on this attack, we present the first end-to-end IPI exploits under natural queries and realistic external corpora, spanning both RAG and agentic systems with diverse attack objectives. These results establish IPI as a practical and severe threat: when a user issued a natural query to summarize emails on frequently asked topics, a single poisoned email was sufficient to coerce GPT-4o into exfiltrating SSH keys with over 80% success in a multi-agent workflow. We further evaluate several defenses and find that they are insufficient to prevent the retrieval of malicious text, highlighting retrieval as a critical open vulnerability.

Related papers

• Silent Egress: When Implicit Prompt Injection Makes LLM Agents Leak Without a Trace [0.0]
  We show that adversarial instructions embedded in automatically generated URL previews can introduce a system-level risk that we refer to as silent egress.<n>Using a fully local and reproducible testbed, we demonstrate that a malicious web page can induce an agent to issue outbound requests that exfiltrate sensitive runtime context.<n>In 480 experimental runs with a qwen2.5:7b-based agent, the attack succeeds with high probability (P (egress) =0.89), and 95% of successful attacks are not detected by output-based safety checks.
  arXiv  Detail & Related papers  (2026-02-25T22:26:23Z)
• The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search [58.8834056209347]
  Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs.<n>We introduce the Correlated Knowledge Attack Agent (CKA-Agent), a dynamic framework that reframes jailbreaking as an adaptive, tree-structured exploration of the target model's knowledge base.
  arXiv  Detail & Related papers  (2025-12-01T07:05:23Z)
• Friend or Foe: How LLMs' Safety Mind Gets Fooled by Intent Shift Attack [53.34204977366491]
  Large language models (LLMs) remain vulnerable to jailbreaking attacks despite their impressive capabilities.<n>In this paper, we introduce ISA (Intent Shift Attack), which obfuscates LLMs about the intent of the attacks.<n>Our approach only needs minimal edits to the original request, and yields natural, human-readable, and seemingly harmless prompts.
  arXiv  Detail & Related papers  (2025-11-01T13:44:42Z)
• External Data Extraction Attacks against Retrieval-Augmented Large Language Models [70.47869786522782]
  RAG has emerged as a key paradigm for enhancing large language models (LLMs)<n>RAG introduces new risks of external data extraction attacks (EDEAs), where sensitive or copyrighted data in its knowledge base may be extracted verbatim.<n>We present the first comprehensive study to formalize EDEAs against retrieval-augmented LLMs.
  arXiv  Detail & Related papers  (2025-10-03T12:53:45Z)
• Revisiting Backdoor Attacks on LLMs: A Stealthy and Practical Poisoning Framework via Harmless Inputs [54.90315421117162]
  We propose a novel poisoning method via completely harmless data.<n>Inspired by the causal reasoning in auto-regressive LLMs, we aim to establish robust associations between triggers and an affirmative response prefix.<n>We observe an interesting resistance phenomenon where the LLM initially appears to agree but subsequently refuses to answer.
  arXiv  Detail & Related papers  (2025-05-23T08:13:59Z)
• Practical Reasoning Interruption Attacks on Reasoning Large Language Models [0.24963930962128378]
  Reasoning large language models (RLLMs) have demonstrated outstanding performance across a variety of tasks, yet they also expose numerous security vulnerabilities.<n>Recent work has identified a distinct "thinking-stopped" vulnerability in DeepSeek-R1 under adversarial prompts.<n>We develop a novel prompt injection attack, termed reasoning interruption attack, and offer an initial analysis of its root cause.
  arXiv  Detail & Related papers  (2025-05-10T13:36:01Z)
• ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models [55.93380086403591]
  Generative large language models are vulnerable to backdoor attacks.<n>$textitELBA-Bench$ allows attackers to inject backdoor through parameter efficient fine-tuning.<n>$textitELBA-Bench$ provides over 1300 experiments.
  arXiv  Detail & Related papers  (2025-02-22T12:55:28Z)
• Document Screenshot Retrievers are Vulnerable to Pixel Poisoning Attacks [72.4498910775871]
  Vision-language model (VLM)-based retrievers leverage document screenshots embedded as vectors to enable effective search and offer a simplified pipeline over traditional text-only methods.<n>In this study, we propose three pixel poisoning attack methods designed to compromise VLM-based retrievers.
  arXiv  Detail & Related papers  (2025-01-28T12:40:37Z)
• GASLITEing the Retrieval: Exploring Vulnerabilities in Dense Embedding-based Search [5.195873909474138]
  embedding-based text retrievalx2013$retrieval of relevant passages from corporax2013$ has emerged as a powerful method state attaining deep learning.<n>However embedding-based retrieval may be susceptible to search-engine adversaries promoting malicious content.
  arXiv  Detail & Related papers  (2024-12-30T13:49:28Z)
• You Know What I'm Saying: Jailbreak Attack via Implicit Reference [22.520950422702757]
  This study identifies a previously overlooked vulnerability, which we term Attack via Implicit Reference (AIR) AIR decomposes a malicious objective into permissible objectives and links them through implicit references within the context. Our experiments demonstrate AIR's effectiveness across state-of-the-art LLMs, achieving an attack success rate (ASR) exceeding 90% on most models.
  arXiv  Detail & Related papers  (2024-10-04T18:42:57Z)
• Backdoor Attacks on Dense Retrieval via Public and Unintentional Triggers [46.19574403393449]
  This paper investigates a novel attack scenario where the attackers aim to mislead the retrieval system into retrieving the attacker-specified contents.<n>Those contents, injected into the retrieval corpus by attackers, can include harmful text like hate speech or spam.<n>Unlike prior methods that rely on model weights and generate conspicuous, unnatural outputs, we propose a covert backdoor attack triggered by grammar errors.
  arXiv  Detail & Related papers  (2024-02-21T05:03:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.