Mind your key: An Empirical Study of LLM API Credential Leakage in iOS Apps

• URL: http://arxiv.org/abs/2606.12212v1
• Date: Wed, 10 Jun 2026 15:29:05 GMT
• Title: Mind your key: An Empirical Study of LLM API Credential Leakage in iOS Apps
• Abstract summary: This study is the first in-depth empirical study of API key leakage in LLM-integrated apps.<n>We construct a high-quality dataset of 444 iOS applications, filtered from 1092 candidates through a standardized process.<n>Our analysis reveals that 282 applications expose exploitable LLM API credentials in network traffic, spanning at least ten providers.
• Score: 5.589937672097304
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The rapid integration of large language models (LLMs) into mobile applications has introduced a new class of credential security risk: leaked credentials that grant unauthorized access to LLM inference services, causing financial damage to developers. Prior work on credential leakage has focused primarily on Android apps; to date, no empirical study has systematically investigated LLM API key leakage in iOS applications. We present the first in-depth empirical study of API key leakage in LLM-integrated apps. We construct a high-quality dataset of 444 iOS applications, filtered from 1092 candidates through a standardized process, and develop LLMKeyLens, a dynamic analysis framework that detects LLM API key leakage via traffic interception, provider-specific key extraction, and active validity confirmation, requiring neither source code access nor binary decryption. Our analysis reveals that 282 applications expose exploitable LLM API credentials in network traffic, spanning at least ten providers. We identify three leakage patterns: JWT-based token leakage (48%), unauthenticated backend proxy access (33%), and plaintext API key transmission (19%). To assess remediation, we re-analyzed the same 282 vulnerable applications three months after responsible disclosure; only 28% had remediated the reported vulnerability, while 72% remained exploitable, with persistent issues stemming from unauthenticated backends and broken JWT implementations. Our findings show that LLM API key leakage is both prevalent and persistent in the iOS ecosystem, exposing a systemic gap between developer practice and secure integration principles, and suggest that secure LLM integration requires not only developer awareness but also explicit security guidance from providers and platform-level enforcement.

Related papers

• Understanding and Mitigating Prompt Leaking Attacks in Real-World LLM-Based Applications [57.33208520608409]
  This paper presents a systematic study of prompt leaking in large language model (LLM)-based applications.<n>We find that over 80% of deployments leak system prompts under realistic adversarial queries.<n>We propose AREA, a practical defense that re-anchors the model's attention using an optimizable soft prompt.
  arXiv  Detail & Related papers  (2026-06-17T04:20:00Z)
• Towards Demystifying and Repairing LLM-in-the-Loop Vulnerabilities [22.313168715963315]
  Large Language Models (LLMs) have been actively integrated into modern software systems as critical components.<n>LLMs-in-the-loop vulnerabilities, where vulnerabilities are introduced by LLMs and their dependent downstream components, such as frameworks, introduce new risks.<n>These vulnerabilities are more challenging to precisely fix, especially for those involving prompt injections where the Pass@1 rate is only 28.57%.
  arXiv  Detail & Related papers  (2026-05-27T08:11:37Z)
• SecPI: Secure Code Generation with Reasoning Models via Security Reasoning Internalization [50.71047638695205]
  Reasoning language models (RLMs) are increasingly used in programming.<n>Yet, even state-of-the-art RLMs frequently introduce critical security vulnerabilities in generated code.<n>We present SecPI, a fine-tuning pipeline that teaches RLMs to internalize structured security reasoning.
  arXiv  Detail & Related papers  (2026-04-04T04:29:11Z)
• Credential Leakage in LLM Agent Skills: A Large-Scale Empirical Study [51.717224133855886]
  Third-party skills extend LLM agents with powerful capabilities but often handle sensitive credentials in privileged environments.<n>We analyze 17,022 skills (sampled from 170,226 on SkillsMP) using static analysis, sandbox testing, and manual inspection.<n>We identify 520 vulnerable skills with 1,708 issues and derive a taxonomy of 10 leakage patterns (4 accidental and 6 adversarial)
  arXiv  Detail & Related papers  (2026-04-03T14:50:16Z)
• Okara: Detection and Attribution of TLS Man-in-the-Middle Vulnerabilities in Android Apps with Foundation Models [3.9807330903947378]
  Transport Layer Security (TLS) is fundamental to secure online communication.<n>Man-in-the-Middle (MitM) attacks remain a pervasive threat in Android apps.<n>We present Okara, a framework that automates the detection and attribution of MitM Vulnerabilities.
  arXiv  Detail & Related papers  (2026-01-30T09:49:09Z)
• "MCP Does Not Stand for Misuse Cryptography Protocol": Uncovering Cryptographic Misuse in Model Context Protocol at Scale [27.85822797774986]
  The Model Context Protocol (MCP) is emerging as the interface for tool integration.<n>MCP provides no guarantees of authenticity or confidentiality, forcing developers to implement cryptography themselves.<n>We presentYSCOPE, the first domain-specific framework for detecting cryptographic misuses in MCP implementations.<n>Our study establishes the first ecosystem-wide view of cryptographic misuse in MCP and provides both tools and insights to strengthen the security foundations of this rapidly growing protocol.
  arXiv  Detail & Related papers  (2025-12-03T13:25:59Z)
• 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)
• LLM-HyPZ: Hardware Vulnerability Discovery using an LLM-Assisted Hybrid Platform for Zero-Shot Knowledge Extraction and Refinement [2.128195197142326]
  LLM-HyPZ is a hybrid framework for zero-shot knowledge extraction and refinement from vulnerability corpora.<n>Applying LLM-HyPZ to the 2021-2024 CVE corpus (114,836 entries), we identified 1,742 hardware-related vulnerabilities.<n> Benchmarking across seven LLMs shows that LLaMA 3.3 70B achieves near-perfect classification accuracy (99.5%) on a curated validation set.
  arXiv  Detail & Related papers  (2025-08-31T00:55:31Z)
• LLMs Caught in the Crossfire: Malware Requests and Jailbreak Challenges [70.85114705489222]
  We propose MalwareBench, a benchmark dataset containing 3,520 jailbreaking prompts for malicious code-generation.<n>M MalwareBench is based on 320 manually crafted malicious code generation requirements, covering 11 jailbreak methods and 29 code functionality categories.<n>Experiments show that mainstream LLMs exhibit limited ability to reject malicious code-generation requirements, and the combination of multiple jailbreak methods further reduces the model's security capabilities.
  arXiv  Detail & Related papers  (2025-06-09T12:02:39Z)
• Unveiling the Landscape of LLM Deployment in the Wild: An Empirical Study [7.5198516000202105]
  Large language models (LLMs) are increasingly deployed through open-source and commercial frameworks.<n>As LLM deployments become prevalent, particularly in industry, ensuring their secure and reliable operation has become a critical issue.<n>Insecure defaults and misconfigurations often expose LLM services to the public internet, posing serious security and system engineering risks.
  arXiv  Detail & Related papers  (2025-05-05T09:30:19Z)
• Exploring Automatic Cryptographic API Misuse Detection in the Era of LLMs [60.32717556756674]
  This paper introduces a systematic evaluation framework to assess Large Language Models in detecting cryptographic misuses. Our in-depth analysis of 11,940 LLM-generated reports highlights that the inherent instabilities in LLMs can lead to over half of the reports being false positives. The optimized approach achieves a remarkable detection rate of nearly 90%, surpassing traditional methods and uncovering previously unknown misuses in established benchmarks.
  arXiv  Detail & Related papers  (2024-07-23T15:31:26Z)
• Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection [64.67495502772866]
  Large Language Models (LLMs) are increasingly being integrated into various applications. We show how attackers can override original instructions and employed controls using Prompt Injection attacks. We derive a comprehensive taxonomy from a computer security perspective to systematically investigate impacts and vulnerabilities.
  arXiv  Detail & Related papers  (2023-02-23T17:14:38Z)

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.