PromptArmor 发布 FrontierBreach 基准,用于衡量企业智能体工作流遭隐藏指令攻击的成功率。该基准在 21 个 AI 模型上的测试中,隐藏攻击平均成功率为 34.9%,其中 Grok 4.5 被攻破的比例达 91.4%,藏在 agent skills 中的攻击成功率为 45.5%。
FrontierBreach 给出了 21 个模型在隐藏指令攻击下的成功率分布,可用来对照企业智能体工作流的安全边界。
PromptArmor has released FrontierBreach, a benchmark of how often AI agents at work can be misled by hidden instructions.
Attackers can hide an invisible line in an email or document, and agents may try to follow it, sending data out or running the attacker's code.
Across 21 AI models, these hidden attacks worked on 34.9% of PromptArmor's tests.
PromptArmor breached every frontier model it tested, from Gemini Argon at 4.3% to Muse Wonder at 15.2%, with Grok 4.5 falling for 91.4% of the attacks.
Attacks hidden inside agent skills also worked in 45.5% of the tests.
Today we’re releasing FrontierBreach, a new standard for attack success rate on agentic workflows in the enterprise. Existing benchmarks systematically underrepresent the security risks facing modern AI agents. FrontierBreach reflects attack scenarios on realistic enterprise workflows, while using sophisticated attack chains that result in cyber consequences (ransomware, data exfiltration, phishing, etc).在 X 查看被引用的帖子
来源:🚨 AI News | TestingCatalog · x.com