AI & ML
Eight in Ten LLMs Leak System-Prompt Secrets: Nevan, an Agentic Capture-the-Flag Study
arXiv cs.CR0 views
arXiv:2611.21956v1 Announce Type: new 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 which techniques. Each model guards a secret 16-character flag set in its system prompt, while an artificial intelligence (AI) agent (OpenCode, powered by DeepSeek V4.1 Flash), steered by a human researcher, tries to persuade it to emit the flag. The flag was exfiltrated from 296 of the 363 models, plus four models released after the initial catalog freeze, for 300 captures in total. Of these, 170 involved a non-English language pivot, most often French. Each capture shows that a model ranked a user request above its system instruction at least once. It does not show that the model provably resists untested attacks, nor that it would consistently leak semantically sensitive data, nor that it is vulnerable to harmful-content jailbreaks. For practitioners, we draw three lessons: do not store secrets in system prompts, enforce critical behavior outside the model with output validation and deterministic checks, and do not let a large language model (LLM) judge be the sole decider of consequential outcomes.
Source:https://arxiv.org/abs/2611.21956PreviousPersonaHate: A Scalable Persona-Based Data Synthesis Pipeline for Hate Speech AnalysisNextHierarchical Personalized Federated Learning for Fine-Grained Intrusion Detection: A Multi-Class Analysis in Heterogeneous Attack Environments
Related posts
How Far Behind Are Open Weights, Measured
0dev.to
Claude was trained on protein sequences at scale
0Hacker News
Pretraining vs post-training: one apple problem, four learning signals
0dev.to Beginners
Bitcoin Recovery Expert USA: Professional Crypto Asset Recovery with META TECH RETRIEVE PRO
0dev.to Beginners
Hugging Face Switches Its Inference Providers to OpenRouter Routing
0dev.to OpenSource
Still confused about Git vs GitHub?
0dev.to Git