52/100

Moderate evidence

Trace: a gain and a problemPublished recordCrimeThe Trace

GapLeak: When Privacy-Preserving LLM-based Web Agents Become a Privacy Risk

Truvace record
TRV-2026-3044raw data (JSON)
Version
v1Published
First published
Evidence type
Benchmark or lab evaluation
Sources
1 sourcePeer-reviewed
sha256
142416254ffe…check it

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 formali…

51Gain side

How the two sides scoreClose call

48Problem side

The gain

In tests on three web-agent frameworks and six LLMs, a submission-time verification filter removed over 96% of unauthorized disclosures while preserving task success.

The problem

In tests of three web-agent frameworks and six LLMs from Anthropic, Google and OpenAI, a GapLeak attack through an ordinary web form induced an average unauthorized disclosure of about 37%.

A fixed formula sets both scores from the evidence and its sources. Reader votes don’t move them.

What the scores mean

G is the gain side, out of 100. It goes up when the gain is specific, when it measurably helped people and when the sources behind it are strong.

P is the problem side, out of 100. It goes up when the problem is specific, when it measurably hurt people and when the sources behind it are strong.

What this doesn’t fix

Instruction-level least-privilege defenses only partially mitigated the leakage and often reduced task success, so existing protections remain incomplete.

Sources

1 on file
  1. Peer-reviewed2026-11-17

Cite this record

v1

Truvace Impact Record TRV-2026-3044, v1: “GapLeak: When Privacy-Preserving LLM-based Web Agents Become a Privacy Risk.” Truvace, 2026-11-19. /record/TRV-2026-3044 (accessed on the day you copy it). sha256 142416254ffe1a09…

Change history

1 version

Every change made to this record since it was first published, and why. Nothing has changed since it went up.

  1. Publishedv1142416254ffe…

    Certified into the record

Check this record hasn’t been altered

Check this record hasn’t been altered
How to check it yourself, without trusting this page

Download any version from /api/record/TRV-2026-3044 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.