Large-scale analysis of 1.2B URLs identifies 15.3K indirect prompt injection instances in the wild, mostly targeting AI systems with up to 8% compliance in model experiments.
https://developers.google.com/sear ch/docs/essentials/spam-policies#hidden-text-and-links
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Indirect Prompt Injection in the Wild: An Empirical Study of Prevalence, Techniques, and Objectives
Large-scale analysis of 1.2B URLs identifies 15.3K indirect prompt injection instances in the wild, mostly targeting AI systems with up to 8% compliance in model experiments.