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

#llm-guards

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

Stories per day · 30 days

Relatedagentdojo2 agent-security2 false-positives2 benchmark1 multilingual1 tool-calls1

2 stories, newest first · one card per story

arXiv cs.CR9d ago

Tool-call guards fail when actions are rendered as shell commands

Four of five specialized guards raise AgentDojo false-positive rates by 21 to 47 points under shell form.

agent-security tool-calls

arXiv cs.CR10d ago

Language Is a Security Surface for Agent Guards

Most smaller agent guards change safety verdicts when requests are translated, especially into rarer languages.

agent-security llm-guards

5