NewA calmer, faster ZeroHour — security assessments on articles, story timelines and search from any page.

#runtime-monitors

1 stories this week · 2 this month · 2 in 6 months · mostly AI

Stories per day · 30 days

Relatedagent-security1 evidence-paths1 formal-methods1 framework-boundaries1 isabelle1 llm-agents1 llm-safety1 prompt-injection1

2 stories, newest first · one card per story

arXiv cs.CR3d ago

PlanTERS formalizes relative security of prompt injection in agents

Revoking injectable tools at the first untrusted read is proved relatively secure on finite runs.

prompt-injection llm-agents

arXiv cs.CR26d ago

LLM safety monitors can drop recognized evidence before enforcement

Authors confirm 18 evidence-path failures across 11 project groups, 14 of which reach enforcement boundaries.

llm-safety agent-security

1