Cryptography and Security · arXiv:2512.11147 v2 · submitted 11 Dec 2025
MiniScope: Authorizing Agents with Least-Privilege Permissions
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
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.
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.
| Sentence | Role | The authors' own work | States the main conclusion | Strength |
|---|---|---|---|---|
| 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
Reviewed papers on Pith that cite this one. The full citation record
- CapLite: Prompt-Injection Defense for Small Language Model Agents without Model-Written Security Artifacts cs.AI · Nov 2026
- From Procedures to Permissions: Learning Precise Subagent Authorization from Agent Skills cs.CL · Nov 2026
- Preference Is Not Permission: Personalizing the Auto-Purchase Line in Agentic Commerce cs.IR · Oct 2026
- Assurance-Conditioned Continuous Authorization for Autonomous AI Agents cs.AI · Nov 2026
- AgentCap: Capability-Based Runtime Authorization for Secure LLM Agent Execution cs.CR · Oct 2026
- FAOPs: Normal Forms and an Algebra for AI Agent Workflows cs.AI · Oct 2026
- CreepScope: Measuring Post-Use Authorization Exposure in Tool-Using Agents cs.CR · Oct 2026
- ToFu: Exploiting and Fuzzing the LLM-Orchestrator-Tool Trust Boundary cs.CR · Oct 2026
- Rethinking Access Control for AI Agents: Recent Advances and Open Challenges cs.SE · Nov 2026
How the literature uses it
19 arXiv papers cite this in 27 sentences
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
-
SkillScope derives task-specific privileges through static graph and replay analysis [ref] , while MiniScope reconstructs provider permission hierarchies from OAuth configurations [ref] .
Do User-Authored Permission Policies Improve Protection Against AI Agent Overreach? · Related Work · 0.95
-
A parallel line of work focuses on dynamic authorization, enforcing the principle of least privilege by restricting tool-calling capabilities as the execution context evolves [ref] .
Efficient and Sound Probabilistic Verification for AI Agents · Related Work · 0.96
-
MiniScope and related least-privilege agent work are direct conceptual neighbors [ref] .
Capability Gates Are Not Authorization: Confused-Deputy Failures in LLM Agent Frameworks · Related Work · 0.86
Challenges and discussion
Know something about this paper? Leave a comment.
Come back by email
A short list of the week's newly reviewed papers. Nothing is sent until you confirm from your inbox, and every email has a link that stops it. No account.
No comments yet.
Sign in to comment