# One Goal, Many Commands: Characterizing Denylist Fragility in AI Agents

arXiv: https://arxiv.org/abs/2606.15549 · HTML: https://mlsanity.com/paper/2606.15549/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 19 of its 52 references that are in the map.
- First posted on arXiv 14 Jun 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 19 of 19)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks](https://mlsanity.com/paper/2404.02151/) (2024)
- [Prompt Injection Attack to Tool Selection in LLM Agents](https://mlsanity.com/paper/2504.19793/) (2025)
- [Progent: Securing AI Agents with Privilege Control](https://mlsanity.com/paper/2504.11703/) (2025)
- [IsolateGPT: An Execution Isolation Architecture for LLM-Based Agentic Systems](https://mlsanity.com/paper/2403.04960/) (2024)
- [LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation](https://mlsanity.com/paper/2409.20550/) (2024)
- [HalluLens: LLM Hallucination Benchmark](https://mlsanity.com/paper/2504.17550/) (2025)
- [Taming Various Privilege Escalation in LLM-Based Agent Systems: A Mandatory Access Control Framework](https://mlsanity.com/paper/2601.11893/) (2026)
- [Terminal-World: Scaling Terminal-Agent Environments via Agent Skills](https://mlsanity.com/paper/2605.20876/) (2026)
- [LLM in the Shell: Generative Honeypots](https://mlsanity.com/paper/2309.00155/) (2023)
- ["Your AI, My Shell": Demystifying Prompt Injection Attacks on Agentic AI Coding Editors](https://mlsanity.com/paper/2509.22040/) (2025)
- [Reframing LLM Agent Security as an Agent-Human Interaction Problem](https://mlsanity.com/paper/2605.24309/) (2026)
- [What You Approve Is What Executes: Consent Integrity for Black-Box LLM Agents](https://mlsanity.com/paper/2606.02668/) (2026)
- [Takedown: How It's Done in Modern Coding Agent Exploits](https://mlsanity.com/paper/2509.24240/) (2025)
- [SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses](https://mlsanity.com/paper/2510.15476/) (2025)

## Built on by (most cited first, 1 of 1)

- [The Balkanization of Execution-Security Research for AI Coding Agents: Isolation, Access Control, and Time-of-Check-to-Time-of-Use Vulnerabilities](https://mlsanity.com/paper/2607.05743/) (2026)

## Abstract (arXiv)

The adoption of AI agents is increasing rapidly. Terminal AI agents, i.e., AI agents that run in terminal environments, are a widely used type of AI agents. Terminal AI agents rely heavily on shell command execution to interact with the host systems. They adopt a three-list command-gating mechanism to mitigate security risks introduced by command execution, with denylists serving as the load-bearing component. However, modern operating systems often ship a large, ever-expanding set of shell commands with complex functionalities. Our observation is that even a built-in denylist of Claude Code, well-maintained by its developers, can overlook bypass commands that invalidate its effectiveness. Such negligence leads to fragile command denylists that cannot even block operations that practitioners expect them to block. This paper presents the first systematic characterization of command denylist fragility in terminal AI agents. The paper formalizes the command denylist fragility problem and proposes an LLM-driven pipeline, ShellSieve, to detect such fragility. It prompts the LLM to propose possible bypasses and iteratively repairs them using feedback from a validator that executes them in a sandbox. In the evaluation, we applied ShellSieve to 1,709 real-world command denylists (containing 13,332 denylist rules) collected from GitHub. The evaluation shows several key findings, including that 69.0--98.6% of the denylists are fragile, that this fragility occurs consistently across projects and agents, and the validity of several possible root causes for this fragility. Our pipeline and findings will hopefully facilitate future research and practice regarding the command denylists used by AI agents.