Don't Let AI Agents YOLO Your Files: Shifting Information and Control to Filesystems for Agent Safety and Autonomy
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914478819377152 |
|---|---|
| author | Zhong, Shawn Wanxiang Liao, Junxuan Liu, Jing Zheng, Mai Arpaci-Dusseau, Andrea C. Arpaci-Dusseau, Remzi H. |
| author_facet | Zhong, Shawn Wanxiang Liao, Junxuan Liu, Jing Zheng, Mai Arpaci-Dusseau, Andrea C. Arpaci-Dusseau, Remzi H. |
| contents | AI coding agents operate directly on users' filesystems, where they regularly corrupt data, delete files, and leak secrets. Current approaches force a tradeoff between safety and autonomy: unrestricted access risks harm, while frequent permission prompts burden users and block agents. To understand this problem, we conduct the first systematic study of agent filesystem misuse, analyzing 290 public reports across 13 frameworks. Our analysis reveals that today's agents have limited information about their filesystem effects and insufficient control over them. We therefore argue for shifting this information and control to the filesystem itself.
Based on this principle, we design YoloFS, an agent-native filesystem with three techniques. Staging isolates all mutations before commit, giving users corrective control. Snapshots extend this control to agents, letting them detect and correct their own mistakes. Progressive permission provides users with preventive control by gating access with minimal interaction. To evaluate YoloFS, we introduce a new methodology that captures user-agent-filesystem interactions. On 11 tasks with hidden side effects, YoloFS enables agent self-correction in 8 while keeping all effects staged and reviewable. On 112 routine tasks, YoloFS requires fewer user interactions while matching the baseline success rate. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_13536 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Don't Let AI Agents YOLO Your Files: Shifting Information and Control to Filesystems for Agent Safety and Autonomy Zhong, Shawn Wanxiang Liao, Junxuan Liu, Jing Zheng, Mai Arpaci-Dusseau, Andrea C. Arpaci-Dusseau, Remzi H. Operating Systems AI coding agents operate directly on users' filesystems, where they regularly corrupt data, delete files, and leak secrets. Current approaches force a tradeoff between safety and autonomy: unrestricted access risks harm, while frequent permission prompts burden users and block agents. To understand this problem, we conduct the first systematic study of agent filesystem misuse, analyzing 290 public reports across 13 frameworks. Our analysis reveals that today's agents have limited information about their filesystem effects and insufficient control over them. We therefore argue for shifting this information and control to the filesystem itself. Based on this principle, we design YoloFS, an agent-native filesystem with three techniques. Staging isolates all mutations before commit, giving users corrective control. Snapshots extend this control to agents, letting them detect and correct their own mistakes. Progressive permission provides users with preventive control by gating access with minimal interaction. To evaluate YoloFS, we introduce a new methodology that captures user-agent-filesystem interactions. On 11 tasks with hidden side effects, YoloFS enables agent self-correction in 8 while keeping all effects staged and reviewable. On 112 routine tasks, YoloFS requires fewer user interactions while matching the baseline success rate. |
| title | Don't Let AI Agents YOLO Your Files: Shifting Information and Control to Filesystems for Agent Safety and Autonomy |
| topic | Operating Systems |
| url | https://arxiv.org/abs/2604.13536 |