RESEARCHInvestigateNEXT 12 MONTHS
Toward Metacognitive One-Shot Indirect Prompt Injection: Strategy Abstraction Via Outcome-Conditioned Reflection
arXiv cs.CL — Computation and Language
Factual evidence
What the source reports
Researchers introduce SAVOR, a method enabling one-shot indirect prompt injection attacks on tool-using LLM agents without repeated queries.
Open source