The evidence behind the guides

Sources library

Browse by topic or search for a study, author or question. Open evidence notes to see what a source can—and cannot—tell us.

TopicCollection

Sources for Cross-context prompt injection

2 sources

Guide citations are still under editorial review.

Chen and colleagues · 2024 Research study

AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases (original source, new tab)

Demonstrates poisoned retrieval and memory in evaluated agents without requiring model retraining.

Greshake and colleagues · 2023 Research study

Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection (original source, new tab)

Demonstrates indirect instructions through retrieved content in specified applications and prototypes.

Sources retain their original publishers’ rights. Inclusion does not imply endorsement. Saved sources stay in this browser on this device. Dates and source descriptions come from the existing editorial records.