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

arXiv: https://arxiv.org/abs/2604.08407 · HTML: https://mlsanity.com/paper/2604.08407/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 8 of its 45 references that are in the map.
- First posted on arXiv 9 Apr 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 8 of 8)

- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Weight Poisoning Attacks on Pre-trained Models](https://mlsanity.com/paper/2004.06660/) (2020)
- [Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale](https://mlsanity.com/paper/2601.10338/) (2026)
- [Backstabber's Knife Collection: A Review of Open Source Software Supply Chain Attacks](https://mlsanity.com/paper/2005.09535/) (2020)
- [Taxonomy of Attacks on Open-Source Software Supply Chains](https://mlsanity.com/paper/2204.04008/) (2022)
- [The Sorry State of TLS Security in Enterprise Interception Appliances](https://mlsanity.com/paper/1809.08729/) (2018)

## Built on by (most cited first, 13 of 13)

- [Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation](https://mlsanity.com/paper/2606.10749/) (2026)
- [KBF: Knowledge Boundary as Fingerprint for Language Model and Black-Box API Auditing](https://mlsanity.com/paper/2605.29524/) (2026)
- [Protocol-Level Attacks on Agentic Commerce Platforms: A Cross-Platform Taxonomy, AIP-Bench, and Unified Defense](https://mlsanity.com/paper/2607.21824/) (2026)
- [The Proxy Knows Too Much: Sealing LLM API Routers with Attested TEEs](https://mlsanity.com/paper/2606.16358/) (2026)
- [Necessary but Not Sufficient: Temperature Control and Reproducibility in LLM-as-Judge Safety Evaluations](https://mlsanity.com/paper/2606.26185/) (2026)
- [Rewriting the Response Path: Silent Tampering and Provider-Signed Defense in BYOK LLM Agents](https://mlsanity.com/paper/2605.02187/) (2026)
- [CoT-Guard: Small Models for Strong Monitoring](https://mlsanity.com/paper/2605.12746/) (2026)
- [Provably Secure Agent Guardrail](https://mlsanity.com/paper/2605.29251/) (2026)
- [Where Is the Tradeoff in Using Third-Party API Routers for Agentic Software Development?](https://mlsanity.com/paper/2607.23624/) (2026)
- [Position: AI Lock-In Is in Progress, and We Must Be Prepared](https://mlsanity.com/paper/2608.14565/) (2026)
- [When Agents Act on Web3: An Attack-Surface Survey of MCP, Skills, and Tool Calling](https://mlsanity.com/paper/2608.17275/) (2026)
- [When the Agent Becomes the Kernel: A Systematization of Security on the Path to AI-Native Operating Systems](https://mlsanity.com/paper/2609.23700/) (2026)
- [SINGED: Correct Outputs Do Not Certify Safe Execution in LLM Agents](https://mlsanity.com/paper/2609.35889/) (2026)

## Abstract (arXiv)

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.