Agent Security Is a Systems Problem
The paper discusses the importance of treating agent security as a systems problem rather than solely focusing on model robustness. It emphasizes the need for security invariants to be enforced at the system level to prevent real-world attacks on agents. The authors propose core principles based on systems security research to enhance the design of agentic systems.
- ▪Agent security should be approached as a systems problem, treating the AI model as an untrusted component.
- ▪Existing efforts to increase model robustness are deemed insufficient without complementing them with systems security techniques.
- ▪The authors analyze eleven real-world attacks on agents and suggest that systems principles could have prevented these incidents.
3 outlets in our directory ran this story, first to last over 32 hours. All of the coverage we found sits in one bucket: centre. That one-sidedness is itself worth noticing.
- ▪ System prompts are not a security boundary for AI agents — DEV.to (Top)
- ▪ Testing distributed systems with AI agents — GitHub
Hacker News (Newest) files mainly under programming. We currently carry 5,306 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
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/2605.18991 |
| Publication time | Wed, 20 May 2026 14:55:13 +0000 |
| Retrieval time | 2026-05-20T15:05:02.641Z |
| Last seen | 2026-05-20T15:05:02.641Z |
| 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 | iFATzC3bbT8p · 3 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:2605.18991 (cs) [Submitted on 18 May 2026] Title:Agent Security is a Systems Problem Authors:Mihai Christodorescu, Earlence Fernandes, Ashish Hooda, Somesh Jha, Johann Rehberger, Kamalika Chaudhuri, Xiaohan Fu, Khawaja Shams, Guy Amir, Jihye Choi, Sarthak Choudhary, Nils Palumbo, Andrey Labunets, Nishit V. Pandya View a PDF of the paper titled Agent Security is a Systems Problem, by Mihai Christodorescu and Earlence Fernandes and Ashish Hooda and Somesh Jha and Johann Rehberger and Kamalika Chaudhuri and Xiaohan Fu and Khawaja Shams and Guy Amir and Jihye Choi and Sarthak Choudhary and Nils Palumbo and Andrey Labunets and Nishit V.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv.org.
Discussion
0 commentsMore from arXiv.org
