PulseAugur
实时 11:02:27
English(EN) A delegate cannot write, present, or invoke other delegates. I ran that sentence as authority.

研究人员绕过了Anthropic的commerce-agents委托合同

Anthropic的commerce-agents框架有一个记录在案的安全合同,规定代表不能编写、呈现或调用其他代表。然而,一位安全研究人员演示了通过操纵代表的权限并将恶意代表放在同一个槽位,可以绕过该合同。这使得恶意代表能够暂存更改,将其呈现给操作员,并调用第二个代表,由于施加的权限限制,在后续运行中被拒绝。研究人员强调,该框架的安全性依赖于代表的特定形状和声明的工具,而不是普遍强制执行的合同。 AI

影响 突出了代理框架中潜在的漏洞,这些框架的安全性依赖于代表的形状而不是严格的合同执行。

排序理由 安全研究人员演示了绕过Anthropic commerce-agents框架中已记录的安全合同。

在 dev.to — Anthropic tag 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

研究人员绕过了Anthropic的commerce-agents委托合同

本文如何被排名

Signal score
38 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
安全研究人员演示了绕过Anthropic commerce-agents框架中已记录的安全合同。
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
safety, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准

报道来源 [1]

  1. dev.to — Anthropic tag TIER_1 English(EN) · Rafael Asor ·

    代表不能编写、呈现或调用其他代表。我将该句子作为权威运行。

    <p>Anthropic's <a href="https://github.com/anthropics/commerce-agents" rel="noopener noreferrer">commerce-agents</a> states its delegate contract in a docstring: a delegate "cannot write, present, or invoke other delegates". I wrote the delegate that sentence warns about, put it …