Clarification-seeking in LLM agents amplifies prompt injection attack success from ~2% to over 30% across ten frontier models in a new 728-scenario benchmark.
Proceedings of the 1st Workshop for Research on Agent Language Models (REALM 2025) , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents
Clarification-seeking in LLM agents amplifies prompt injection attack success from ~2% to over 30% across ten frontier models in a new 728-scenario benchmark.