Skip to content
AI Atlas
PaperActive

No-Box Vulnerability Analysis: Description-only Detection of Indirect Prompt Injection Vulnerabilities in MCP Servers

arxiv.org/abs/2609.10854

quality89

Updated 2 h ago · first seen 12 Sept 2026

paper_01M29X34SQP986DJ2FHPXFES3B

Published
12 Sept 2026
T1 · 2 h ago
arXiv
2609.10854
T1 · 2 h ago
Category
cs.CR
T1 · 2 h ago

Abstract

Conventional vulnerability analysis relies on either system access or dynamic interaction, all of which may be unavailable to third-party analysts auditing closed-source, remotely hosted, critical in situ systems, or commercially gated software. Therefore, we propose a new paradigm of no-box vulnerability analysis in which neither access nor runtime interaction is available, and only functionality metadata is available. Such metadata defines the intended behavior of the system, including its inputs, outputs, and side effects, while constraining the space of implementations consistent with that behavior. We propose hypothesizing about vulnerabilities that exist across all possible implementations of a given system metadata, without observing or interacting with the target system. An analyst can later validate these hypotheses when additional access is available. We showcase the feasibility of no-box vulnerability analysis through implementing a prototype called MCPSEC, which audits Model Context Protocol (MCP) servers for indirect prompt injection vulnerabilities using only the tool metadata exposed at server registration time. We evaluate MCPSEC on 20 widely deployed MCP servers comprising 177 tools, among which human evaluators confirm 95 vulnerable tools. MCPSEC identified 143 tools as vulnerable, and for each vulnerable tool, it produced a hypothesized vulnerability along with exploitation technique. Using metadata alone, MCPSEC predicted 94 (98.9% recall) real verified vulnerabilities, compared against an LLM baseline with 80 (84.2% recall). Overall, our results introduce no-box vulnerability analysis as a new analysis paradigm and demonstrate its practical feasibility in realistic systems.

Authors 16

Adam Doupe, Aditya Maheshbhai Gabani, Chang Zhu, Divij Handa, Hongkai Chen, Hulin Wang, Jie Hu, Pratham Hegde, Ruoyu Wang, Siyu Liu, Souradip Nath, Tiffany Bao, Yan Shoshitaishvili, Yibo Liu, Zehua Zhang, Zhuoer Lyu

Specification

Official page

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Arxiv announce type
cross

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

arXiv id
2609.10854

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Categories
cs.AI, cs.CR

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

PDF

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Primary category
cs.CR

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Published
12 Sept 2026

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

2 h ago

Conflicts

None