Figshareopen access
AgentBreaker: Evaluating Context-Aware Indirect Prompt Injection Risks in Modern Web Agents (Artifact)
cybersecurity and privacy not elsewhere classified, web agents
This document is indexed with metadata only — full text is not available in the archive for this record.
Open the official source ↗
Record · ID 357092
Retrieved via
Conceptio — every document is proof-bundled with source, license, and retrieval metadata.