agent/papers/items/2026-2604-20994-breaking-mcp-with-function-hijacking-attacks-novel-threats-for-function-calling-.md

Paper: Breaking MCP with Function Hijacking Attacks: Novel Threats for Function Calling and Agentic Models

---

type: paper title: "Breaking MCP with Function Hijacking Attacks: Novel Threats for Function Calling and Agentic Models" authors: Yannis Belkhiter, Giulio Zizzo, Sergio Maffeis, Seshu Tirupathi, John D. Kelleher year: 2026 venue: arXiv url: https://arxiv.org/abs/2604.20994 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-04-22 updated_at: 2026-04-22 status: queued relevance: high topics:

• agent-safety
• reasoning
• tool-use methods:

benchmarks:

models:

datasets:

• cs.CR
• cs.AI
• cs.CL related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 13 collection_queries: function-calling

One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

Why Collected

• matched queries: function-calling
• inferred topics: agent-safety, reasoning, tool-use
• arXiv categories: cs.CR, cs.AI, cs.CL
• collection score: 13

Review Checklist

• Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
• Does it include a benchmark, dataset, code, or reproducible experimental setup?
• Should it be promoted from queued to skimmed or summarized?

Links

• arXiv: https://arxiv.org/abs/2604.20994