Pith.

Cryptography and Security · arXiv:2512.11147 v2 · submitted 11 Dec 2025

MiniScope: Authorizing Agents with Least-Privilege Permissions

Jinhao Zhu, Xiao Huang, Kevin Tseng, Gil Vernik, Shishir G. Patil, Vivian Fang, Raluca Ada Popa

The paper says

“Our evaluation shows that MiniScope reduces simulated permission confirmations by 43.4%-89.4% for cautious and typical personas relative to per-tool prompting and mitigates all privilege-escalation attacks with negligible impact on utility and runtime.”

from the abstract · picked out as the main claim by a classifier

Pith says

Pith has not reviewed this paper.

Get a Pith Review, $5

Reviews

Reviews by people

No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.

Request a human review

How Pith checks papers · The full audit of this paper

The paper

Abstract

AI agents are increasingly granted autonomous access to sensitive user data and third-party services, making effective permission management a critical security challenge. Existing permission models, however, typically rely on flat permission structures that fail to balance security with usability: fine-grained confirmation induces user fatigue, while coarse-grained or persistent approval leads to overprivileged agents. To address this tradeoff, we propose a task-centric, hierarchical permission model that treats an agent as a delegate operating within a task-specific role instead of requiring a separate permission decision for every tool call. Building on this model, we present MiniScope, an end-to-end permission system for agents that automates permission-hierarchy discovery and enforces contextual least privilege at runtime. Our evaluation shows that MiniScope reduces simulated permission confirmations by 43.4%-89.4% for cautious and typical personas relative to per-tool prompting and mitigates all privilege-escalation attacks with negligible impact on utility and runtime. Applied to real-world deployments, MiniScope further uncovers six overprivileged connector configurations in ChatGPT and Claude.

The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.

abstract compiled · 2026-10-07 · no language-model review

How the main claim is stated: asserted 1.00

What the abstract itself states, as probabilities: claims first 0.06 · states limitation 0.13 · human participants 0.35 · controlled comparison 0.90 · randomized assignment 0.02 · states quantitative result 0.99 · compares with prior results 0.94 · mentions code or data availability 0.04

The abstract, sentence by sentence

This table labels the abstract only (arXiv listing abstract v2). The number is the probability the classifier gave the label.

SentenceRoleThe authors' own workStates the main conclusionStrength
AI agents are increasingly granted autonomous access to sensitive user data and third-party services, making effective permission management a critical security challenge. background 1.00 0.04 0.02 asserted 1.00
Existing permission models, however, typically rely on flat permission structures that fail to balance security with usability: fine-grained confirmation induces user fatigue, while coarse-grained or persistent approval leads to overprivileged agents. gap 0.65 0.05 0.03 asserted 1.00
To address this tradeoff, we propose a task-centric, hierarchical permission model that treats an agent as a delegate operating within a task-specific role instead of requiring a separate permission decision for every tool call. method 0.52 0.62 0.09 asserted 0.97
Building on this model, we present MiniScope, an end-to-end permission system for agents that automates permission-hierarchy discovery and enforces contextual least privilege at runtime. contribution 0.91 0.91 0.10 asserted 1.00
Our evaluation shows that MiniScope reduces simulated permission confirmations by 43.4%-89.4% for cautious and typical personas relative to per-tool prompting and mitigates all privilege-escalation attacks with negligible impact on utility and runtime. result 1.00 0.97 0.71 asserted 1.00
Applied to real-world deployments, MiniScope further uncovers six overprivileged connector configurations in ChatGPT and Claude. result 0.99 0.95 0.11 asserted 1.00

What kind of paper the classifier reports this is: method or tool 1.00 · evidence from observation or experiment 0.80

What was examined, and what was not

Sources read

  • arXiv listing abstract v2

Not examined

  • full text
  • figures and tables
  • references and citing sentences
  • relations to other papers

Levels run

  • P abstract

Not run

  • S sections
  • T body sentences
  • C citations
  • R cross-paper relations

How the labels were made

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-10-07: 1 request, 5,046 input tokens.

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON

Cited by 9 Pith papers
How the literature uses it

19 arXiv papers cite this in 27 sentences

Each citing sentence is taken from the citing paper's LaTeX source and typed by Pith's classifier. A label appears at probability 0.8 or more (0.95 for support), a contest at 0.7 or more; the quoted words are the citing authors'. How each label was checked · JSON

Papers citing it · 16 sentences without a confident label

Cites it as support 2 papers
  • We argue for three shifts: replace the refusal primitive with least privilege [ref] ; move enforcement outside the model to a mechanically checked action boundary [ref] ; and evaluate safety as a relational, multi-coordinate property rather than a single refusal score.

    Agent Safety Is Action Alignment · Introduction · 0.97

  • Access-control and information-flow approaches offer a stronger systems-security logic because they constrain what compromised reasoning is allowed to affect [ref] , yet they demand explicit capability models, provenance signals, and engineering effort that many current agent frameworks do not yet expose by default.

    Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation · Defense Families Along the Agentic Loop · 0.98

Cites it as background 7 papers

Challenges and discussion

Know something about this paper? Leave a comment.

No comments yet.

Sign in to comment