Skip to content
Search
paperJuly 2026Unreviewed

The Balkanization of Execution-Security Research for AI Coding Agents: Isolation, Access Control, and Time-of-Check-to-Time-of-Use Vulnerabilities

Mohammadreza Rashidi

View resourcePDF

Abstract

AI coding agents now read repositories, call tools, and execute shell commands with limited human oversight, and a fast-growing body of work studies whether the execution layer around them is actually safe. That literature is scattered. Papers on sandbox isolation, capability and access control, policy enforcement, time-of-check-to-time-of-use (TOCTOU) races, Model Context Protocol (MCP) threats, identity delegation, execution provenance, network egress control, and static analysis of agent-gene

Categories

Access ControlSandboxing & IsolationHuman-in-the-Loop

Cite

@misc{rashidi2026balkanization,
  title = {{The Balkanization of Execution-Security Research for AI Coding Agents: Isolation, Access Control, and Time-of-Check-to-Time-of-Use Vulnerabilities}},
  author = {Mohammadreza Rashidi},
  year = {2026},
  month = jul,
  eprint = {2607.05743},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.05743}
}