arXiv cs.AI· Gangzhen Qian, Kainan Zhou, Chuhong Xu, Hang Xiao, Zhi Jing, Rong Bao, Lu Yi, Zhaoyi Li·· 3 小时前AI 评分39
AI 搜索中 llms.txt 清单辅助检索的安全评估：证据缺口与威胁路径分析
Manifest-Assisted Retrieval in Artificial Intelligence Search: Evidence Gaps and a Security Evaluation
AI 导读
一篇入选 IEEE FLLM 2026 的论文评估了 AI 搜索中 /llms.txt 清单文件的安全与效用证据。初始审计覆盖截至 2026 年 8 月 16 日的 39 个来源，一项 15 工具研究在 45 次试验中未观察到自动请求，另一日志研究显示 2026 年 5 月 97% 检出该文件的域名无记录请求。
正文 · 原文
Abstract:The external sources retained in our non-systematic audit did not isolate the incremental security or utility effect of consuming /llms.txt while ordinary retrieval remained fixed. The initial audit covered 39 sources through August 16, 2026, with later targeted updates through October 14. A purposive 15-tool study observed no automatic requests in 45 trials at one endpoint; a non-probability log study found that 97% of domains with detected files received no recorded requests in May 2026. We separate publication, fetch, model use, and action; define five operational threat paths and paired security-utility estimands; and exercise deterministic pre-model controls with 30 author-defined parser fixtures. We also execute a reduced pilot: 24 tasks across eight sites, five conditions, and 120 real model responses, with ordinary evidence held fixed. Frozen automatic scoring identifies attacker-target adoption in $21/24$ raw adversarial responses, with one further response unresolved; the adversarial URLs-only condition has no known adoptions and one unresolved response. The pilot measures output changes conditional on supplied evidence, without live retrieval or external actions. Together, the framework and pilot distinguish manifest-content effects from publication, discovery, and downstream execution, while leaving full retrieval and agent evaluation open.
| Comments: | 8 pages, 3 figures, 5 table. Accepted at IEEE FLLM 2026. Author accepted manuscript. Reproducibility artifact: this https URL |
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE); Computation and Language (cs.CL); Databases (cs.DB); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2610.38361 [cs.CR] |
| (or arXiv:2610.38361v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.38361 arXiv-issued DOI via DataCite |
Submission history
From: Kainan Zhou [view email]
[v1]
Wed, 28 Oct 2026 06:58:07 UTC (481 KB)
来源：arXiv cs.AI · arxiv.org