Argument-Aware Runtime Least-Privilege Enforcement Against Tool-Poisoning-Induced Actions in MCP-Based Agentic Systems
Future Internet · 04.11.2026 · 18 (11) · 606
DOI: 10.3390/fi18110606 ↗Kurz gefasst
Fachartikel in der Zeitschrift Future Internet, online erschienen am 04.11.2026. Verfasst von Mohammad Nouman und 2 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Tool poisoning can induce Model Context Protocol (MCP) agents to perform harmful host-side actions through manipulated tool metadata or invocation arguments. This paper studies a client-side least-privilege capability-inference mechanism that translates concrete tool names and recursively structured arguments into six behavioural categories before policy lookup. On a review-driven audit of 27 calls labelled from documented official MCP reference-server semantics, the corrected mapper obtains 27/27 exact category sets. On 16 author-instantiated, external-provenance MCPTox cases, it recovers all specified minimum capabilities with three additional conservative categories; neither set constitutes blind generalisation evidence. A separate policy matrix yields 27/27 expected decisions. An independently implemented declared-capability policy comparator agrees with B4 on 170/172 decisions across four profiles, including 43/43 under limited-network (0% ASR; 59.26% benign-call allow rate). Hardened launch validation rejects eight malformed or bypass specifications. Twelve live stdio checks verify tool discovery, two benign workflow outputs, denied-write non-execution, error propagation, ASK denial, symlink protection, and upstream-crash failure. The 20-workflow authorisation replay is reported separately from executed task success. The contribution is automatic name/argument-to-capability inference and bounded enforcement evidence, not universal interception or confinement of malicious server internals.
Zitieren
APA
Nouman, M., Haider, S. I., & Ujjan, R. (2026). Argument-Aware Runtime Least-Privilege Enforcement Against Tool-Poisoning-Induced Actions in MCP-Based Agentic Systems. Future Internet, 18(11), 606. https://doi.org/10.3390/fi18110606
Vancouver
Nouman M, Haider SI, Ujjan R. Argument-Aware Runtime Least-Privilege Enforcement Against Tool-Poisoning-Induced Actions in MCP-Based Agentic Systems. Future Internet. 2026;18(11):606. doi:10.3390/fi18110606
BibTeX
@article{Nouman2026,
author = {Nouman, Mohammad and Haider, Syed Ijlal and Ujjan, Raja},
title = {Argument-Aware Runtime Least-Privilege Enforcement Against Tool-Poisoning-Induced Actions in MCP-Based Agentic Systems},
journal = {Future Internet},
year = {2026},
volume = {18},
number = {11},
pages = {606},
doi = {10.3390/fi18110606}
}
EUVIMED