arxiv
PublishedNovember 18, 2026 at 5:00 AM
Eight in Ten LLMs Leak System-Prompt Secrets: Nevan, an Agentic Capture-the-Flag Study
Publisher summary· verbatim
arXiv:2611.21956v1 Announce Type: cross Abstract: We audit instruction-hierarchy enforcement across 363 text-in/text-out models from the OpenRouter catalog. The research question we answer with this experiment is which models disclose a protected secret embedded in the system prompt, and through whi
Stay posted· Newsletter
Three short emails a week: Monday, Wednesday and Friday. Top movers, new models and the most-referenced story.
Your email is used only to send The Bubble Brief. Privacy policy
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivReadie: Low-Latency Code Sandboxes for AI Agents14hThe Bubble Brief
MON · WED · FRIRead AI insights every Monday, Wednesday and Friday — top movers, new models, story of the week.
Your email is used only to send The Bubble Brief. Privacy policy
Originally published on arxiv ↗