cs.CROct 29, 2026

"Shall We Approve?" Consequence-Aware Approval for Autonomous Coding Agents

Authors: Weiheng Wu, Junkai Chen, Zhensu Sun, Jieke Shi, Yunbo Lyu, David Lo

Organizations: Singapore Management University

Abstract

Coding agents increasingly rely on automated approvers to decide whether a proposed shell command may run. Existing approvers, from rule-based checkers to guardrail models and deployed permission classifiers, base their decisions on the text of the request and command. Yet a command's behavior depends on the code it invokes and the state of the workspace, and systems that observe file changes leave the assessment to the agent or a human after execution. We present Caper, a consequence-aware approval mechanism that pre-executes each command in a snapshotted sandbox, provides an independent approver with a bounded report of its observed effects, commits allowed commands, and rolls back blocked ones with a reason the agent can act on. Compared with six existing systems, Caper achieves the lowest harmful-outcome rate on SABER (6.7% versus at least 14.8%) and YoloFS-Ext, a benchmark we build in which harmful behavior is hidden inside invoked tools (7.8% versus at least 35.3%), while blocking 1.0% of the safe twins of the dangerous tasks in YoloFS-Ext.

Figures & tables

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. From Approval to Abuse: Privilege Escalation Attacks on Harness-Protected Coding Agents

    Oct 16, 2026Xianglin Yang, Yechao Zhang, Jiahao Liu +4AI Agent SecurityLLM Agent Harnesses

  2. Measuring the Permission Gate: A Stress-Test Evaluation of Claude Code's Auto Mode

    Apr 4, 2026Zimo Ji, Zongjie Li, Pingchuan Ma +3AI Agent SecurityTool-Use Authorization