SOURCE-LINKED INTELLIGENCE

Context Inference Attacks Without Jailbreaks

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Agentic AI systems are increasingly deployed to process sensitive data at inference time, such as healthcare records or financial documents assembled into a hidden \emph{context} before the system answers. Prior work has studied privacy risks primarily through \emph{jailbreaking} attacks that induce models to directly disclose sensitive content, but has largely overlooked the agentic setting where the context is assembled by the agent's own tool calls. We show that the agents we evaluate remain vulnerable to hidden-context leakage despite the controls we test against them, namely an instructio

Read original source ↗ Open in workspace

recordType

paper

region

Global