Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply Chain

• URL: http://arxiv.org/abs/2604.08407v1
• Date: Thu, 09 Apr 2026 16:06:41 GMT
• Title: Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply Chain
• Abstract summary: Large language model (LLM) agents increasingly rely on third-party API routers to dispatch tool-calling requests.<n>We present the first systematic study of this attack surface.
• Score: 6.142057368768942
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Large language model (LLM) agents increasingly rely on third-party API routers to dispatch tool-calling requests across multiple upstream providers. These routers operate as application-layer proxies with full plaintext access to every in-flight JSON payload, yet no provider enforces cryptographic integrity between client and upstream model. We present the first systematic study of this attack surface. We formalize a threat model for malicious LLM API routers and define two core attack classes, payload injection (AC-1) and secret exfiltration (AC-2), together with two adaptive evasion variants: dependency-targeted injection (AC-1.a) and conditional delivery (AC-1.b). Across 28 paid routers purchased from Taobao, Xianyu, and Shopify-hosted storefronts and 400 free routers collected from public communities, we find 1 paid and 8 free routers actively injecting malicious code, 2 deploying adaptive evasion triggers, 17 touching researcher-owned AWS canary credentials, and 1 draining ETH from a researcher-owned private key. Two poisoning studies further show that ostensibly benign routers can be pulled into the same attack surface: a leaked OpenAI key generates 100M GPT-5.4 tokens and more than seven Codex sessions, while weakly configured decoys yield 2B billed tokens, 99 credentials across 440 Codex sessions, and 401 sessions already running in autonomous YOLO mode. We build Mine, a research proxy that implements all four attack classes against four public agent frameworks, and use it to evaluate three deployable client-side defenses: a fail-closed policy gate, response-side anomaly screening, and append-only transparency logging.

Related papers

• SIR: Self-improving Red-teaming for Compute Use Agents [71.71987044117371]
  Computer use agents (CUAs) are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal.<n>Because they can be exposed to untrusted content while operating, they are vulnerable to indirect prompt injection (IPI)<n>We present SIR, a black box IPI attack that composes stealthy injections from a small library of reusable principles stated in plain language.
  arXiv  Detail & Related papers  (2026-08-31T03:39:43Z)
• LMSM: LLM Security Framework Inspired by Linux Security Modules [56.93644694627783]
  Large language models (LLMs) are increasingly deployed with layered defenses, yet malicious prompts can still bypass them.<n>We present Language Model Security Modules (LMSM), a security framework that adapts the separation behind Linux Security Modules (LSM) to LLM serving.
  arXiv  Detail & Related papers  (2026-08-26T12:13:05Z)
• Beyond the Mandate: A Systematic Security Analysis of the Agent Payments Protocol (AP2) [13.020998549537874]
  AP2 enables large language model (LLM)-driven shopping agents to authorize and execute payments on behalf of users.<n>Prior work identified replay and prompt-injection attacks in AP2 v0.1.<n>We present a systematic security analysis of AP2 v0.2 based on its roles, transaction lifecycle, deployment architectures, and trust boundaries.
  arXiv  Detail & Related papers  (2026-08-24T22:05:00Z)
• Stealing Reasoning Traces from Proprietary LLM APIs [84.58379404903394]
  We develop a scalable decryption jailbreak for encrypted reasoning traces.<n>It circumvents anti-distillation mechanisms, allowing adversaries to extract a proprietary model's reasoning.<n>It inadvertently reveals hazardous information hidden within the reasoning process.
  arXiv  Detail & Related papers  (2026-08-10T17:24:50Z)
• Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens [65.53494487819053]
  Claw-like AI agents (e.g., OpenClaw) are always-on processes with persistent access to credentials, files, tools, and external services.<n>We adopt a computer-system analogy: treating a Claw-like agent as an agentic computer system whose gateway runtime plays an OS-like mediation role.<n>We develop SafeClawArena, a benchmark of 406 adversarial tasks across four attack surfaces.
  arXiv  Detail & Related papers  (2026-06-29T18:00:45Z)
• The Proxy Knows Too Much: Sealing LLM API Routers with Attested TEEs [14.19502587458358]
  AEGIS is a provider-transparent API router whose data path is a client-verified faithful passthrough.<n>We show that all four malicious-router attack classes succeed against a plaintext-access baseline.<n>The trusted path is $851$ lines, carries three provider-native APIs without conversion, and completes every request under real-provider workload and typos.
  arXiv  Detail & Related papers  (2026-06-15T07:55:13Z)
• Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems [35.65937852381774]
  Document-Driven Implicit Payload Execution (DDIPE) embeds malicious logic in code examples and configuration templates within skill documentation.<n>We generate 1,070 adversarial skills from 81 seeds across 15 MITRE ATTACK categories.<n>DDIPE achieves 11.6% to 33.5% bypass rates, while explicit instruction attacks achieve 0% under strong defenses.
  arXiv  Detail & Related papers  (2026-04-03T14:58:58Z)
• AIP: Agent Identity Protocol for Verifiable Delegation Across MCP and A2A [0.0]
  Invocation-Bound Capability Tokens (IBCTs) fuse identity, authorization, and provenance binding into a single append-only token chain.<n>We provide reference implementations in Python and Rust with full cross-language interoperability.
  arXiv  Detail & Related papers  (2026-03-25T19:45:37Z)
• Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain [82.98626829232899]
  Fine-tuning AI agents on data from their own interactions introduces a critical security vulnerability within the AI supply chain.<n>We show that adversaries can easily poison the data collection pipeline to embed hard-to-detect backdoors.
  arXiv  Detail & Related papers  (2025-10-03T12:47:21Z)
• Cuckoo Attack: Stealthy and Persistent Attacks Against AI-IDE [64.47951172662745]
  Cuckoo Attack is a novel attack that achieves stealthy and persistent command execution by embedding malicious payloads into configuration files.<n>We formalize our attack paradigm into two stages, including initial infection and persistence.<n>We contribute seven actionable checkpoints for vendors to evaluate their product security.
  arXiv  Detail & Related papers  (2025-09-19T04:10:52Z)
• A Multi-Agent LLM Defense Pipeline Against Prompt Injection Attacks [1.1435139523855764]
  This paper presents a novel multi-agent defense framework to detect and neutralize prompt injection attacks in real-time.<n>We evaluate our approach using two distinct architectures: a sequential chain-of-agents pipeline and a hierarchical coordinator-based system.
  arXiv  Detail & Related papers  (2025-09-16T19:11:28Z)
• BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks [58.959622170433725]
  BlindGuard is an unsupervised defense method that learns without requiring any attack-specific labels or prior knowledge of malicious behaviors.<n>We show that BlindGuard effectively detects diverse attack types (i.e., prompt injection, memory poisoning, and tool attack) across multi-agent systems.
  arXiv  Detail & Related papers  (2025-08-11T16:04:47Z)
• 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)
• EmInspector: Combating Backdoor Attacks in Federated Self-Supervised Learning Through Embedding Inspection [53.25863925815954]
  Federated self-supervised learning (FSSL) has emerged as a promising paradigm that enables the exploitation of clients' vast amounts of unlabeled data. While FSSL offers advantages, its susceptibility to backdoor attacks has not been investigated. We propose the Embedding Inspector (EmInspector) that detects malicious clients by inspecting the embedding space of local models.
  arXiv  Detail & Related papers  (2024-05-21T06:14:49Z)
• Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [38.25697806663553]
  We show that even the most recent safety-aligned LLMs are not robust to simple adaptive jailbreaking attacks.<n>We achieve 100% attack success rate -- according to GPT-4 as a judge -- on Vicuna-13B, Mistral-7B, Phi-3-Mini, Nemotron-4-340B, Llama-2-Chat-7B/13B/70B, Llama-3-Instruct-8B, Gemma-7B, GPT-3.5, GPT-4o, and R2D2 from HarmBench.
  arXiv  Detail & Related papers  (2024-04-02T17:58:27Z)

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.