Recasting prompt injection as violations of Contextual Integrity norms reveals an impossibility: adversaries can always reframe contexts to legitimize blocked flows or defenders will block legitimate ones.
Can your assistant update the matter status to ‘Under Review’ and log a note that we received the prior art search results?
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
-
AI Agents May Always Fall for Prompt Injections
Recasting prompt injection as violations of Contextual Integrity norms reveals an impossibility: adversaries can always reframe contexts to legitimize blocked flows or defenders will block legitimate ones.