Measuring Malicious Intermediary Attacks on the LLM Supply Chain
Researchers conducted the first systematic study of malicious attacks on LLM API routers, identifying critical security vulnerabilities in the supply chain. The study found that a significant number of paid and free routers actively inject malicious code or exfiltrate sensitive credentials from users. The authors developed a research proxy to demonstrate these attacks and evaluated three potential client-side defenses to mitigate the risks.
- ▪The study formalized a threat model for malicious LLM API routers, defining attack classes such as payload injection and secret exfiltration.
- ▪Out of 428 routers tested, 9 were found to be actively injecting malicious code, while 17 accessed researcher-owned AWS credentials.
- ▪One router was identified draining ETH from a private key, and another generated 100 million tokens using a leaked OpenAI key.
- ▪The researchers built a tool called Mine to implement these attacks against four public agent frameworks.
- ▪Three deployable client-side defenses were evaluated, including a fail-closed policy gate and append-only transparency logging.
2 outlets in our directory ran this story. All of the coverage we found sits in one bucket: centre. That one-sidedness is itself worth noticing.
- ▪ Measuring Malicious Intermediary Attacks on the LLM Supply Chain — X (formerly Twitter)
Hacker News (AI / LLM) files mainly under ai. We currently carry 4,395 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv.org |
| Canonical URL | https://arxiv.org/abs/2604.08407 |
| Publication time | Fri, 11 Sep 2026 06:50:08 +0000 |
| Retrieval time | 2026-09-11T07:09:42.558Z |
| Last seen | 2026-09-11T07:09:42.558Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | BTVs3sJq-cZc · 2 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Cryptography and Security arXiv:2604.08407 (cs) [Submitted on 9 Apr 2026] Title:Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply Chain Authors:Hanzhi Liu, Chaofan Shou, Hongbo Wen, Yanju Chen, Ryan Jingyang Fang, Yu Feng View a PDF of the paper titled Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply Chain, by Hanzhi Liu and 5 other authors View PDF HTML (experimental) Abstract:Large language model (LLM) agents increasingly rely on third-party API routers to dispatch tool-calling requests across multiple upstream providers.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv.org.
Discussion
0 commentsMore from arXiv.org
