Preliminary research

ToFu: Exploiting and Fuzzing the LLM-Orchestrator-Tool Trust Boundary

Md Nazmul Islam Ananto, Pierre Prevost-Avenel, Colin Smith, Kyungtae Kim, Taegyu Kim and Arslan Khan · arXiv · 9 October 2026

AI-collected research leads through 3 November 2026, including a November–October–September missed-article review and a targeted multilingual search alongside earlier community-source sweeps. Unranked, incomplete, not community-vetted, and subject to change.

Derives tool-specific security checks from metadata and a CWE-guided corpus, then fuzzes schema-aware invocations using runtime and outcome oracles. Reports manually reviewed bugs in MCP servers and distinguishes extracted tools from those exercised.

Record

Researcher

Md Nazmul Islam Ananto, Pierre Prevost-Avenel, Colin Smith, Kyungtae Kim, Taegyu Kim and Arslan Khan

Published by

arXiv

Date

9 October 2026

In the archive

• Collected in the 2026 preliminary research sweep

Tags

• mcp
• fuzzing
• input-validation
• tooling

This page is the archive's own catalogue record. The research is the work of Md Nazmul Islam Ananto, Pierre Prevost-Avenel, Colin Smith, Kyungtae Kim, Taegyu Kim and Arslan Khan, first published at the original source. Preserved copies are kept so the citation survives its host.