2023 AD
Indirect prompt injection in agents
Artificial intelligence · Safety and control
Researchers demonstrated that instructions hidden in external content could alter applications integrating language models. The problem exposed a security boundary: an agent must distinguish the data it consults from the authorized instructions it should follow.
Precision, calendar, and review
- Start
- year · no uncertainty qualifier in this record
- Calendar and convention
- Historical-era years; the source calendar is not identified. No conversion of days is assumed.
- Year zero
- The scale goes from 1 BCE to 1 CE without year zero. Changing era names changes labels only.
- Documentary review
- 2026-09-20
Reading the date: point event.
Sources
- arxiv.org (opens in a new tab)
Source provenance and scope
- Publication date
- 2023-02-23
- What this date describes
- The cited source or edition; it may postdate the historical event.
- Date note
- Date of the first arXiv preprint version; later revisions may exist.
- Bibliographic date checked
- 2026-09-23
- Date evidence
- Declared in the cited source’s publisher metadata.
- Access date
- 2026-09-20
The correspondence between this reference and individual claims has not yet been itemized.
This record is an editorial synthesis. Consult the sources to check claims and their limits. Chronological relationships alone do not establish causation.