arXiv · 2611.22223
GapLeak: When Privacy-Preserving LLM-based Web Agents Become a Privacy Risk
Abstract
Large Language Model (LLM)-based web agents rely on data minimization and least privilege to protect user privacy. We show that these principles are necessary but insufficient: they constrain authorized sources, but not higher-sensitivity sources that remain reachable. A website can request a field unavailable from authorized sources, creating an information gap. To complete the task, a goal-driven agent may escalate to reachable but unauthorized sources and disclose accumulated sensitive information. We formalize this vulnerability as GapLeak, where an adversary exploits a legitimate web form without prompt injection or other malicious instructions. We evaluate GapLeak on three web-agent frameworks and six LLMs from Anthropic, Google, and OpenAI across recruitment, e-commerce, travel, and healthcare. GapLeak induces an average unauthorized disclosure of approximately 37%. The information gap is the primary driver: eliminating it reduces disclosure by more than 50%. Existing instruction-level defenses based on least privilege partially mitigate the vulnerability but often reduce task success. We propose submission-time verification, which filters unauthorized content before form submission, eliminating over 96% of unauthorized disclosures while preserving task success.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Chaklam Cheong, Tiancong Cao, Qi Li, Zelin Zhang, Jianbing Ni, Rongxing Lu, Mohammad Zulkernine. 2026-11-17. GapLeak: When Privacy-Preserving LLM-based Web Agents Become a Privacy Risk. https://searcharxiv.com/abs/2611.22223
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.