随着 Claude Code 的普及,大量用户选择通过第三方中转站(API Proxy)来使用 Claude 模型。然而,中转站作为用户与官方 API 之间的中间层,天然具备篡改请求和响应的能力。本文将从上下文空间异常、模型造假、提示词投毒三个维度,揭示中转站可能存在的安全风险,并给出对应的检测方法。
A vulnerability was found in phpseclib up to 1.0.26/2.0.51/3.0.49. It has been classified as problematic. Affected by this vulnerability is an unknown functionality. This manipulation causes observable timing discrepancy.
The identification of this vulnerability is CVE-2026-32935. It is possible to initiate the attack remotely. There is no exploit available.
Upgrading the affected component is recommended.
A vulnerability identified as problematic has been detected in NaturalIntelligence fast-xml-parser up to 5.5.5. Affected is the function replaceEntitiesValue. Performing a manipulation results in xml entity expansion.
This vulnerability is identified as CVE-2026-33036. The attack can be initiated remotely. There is not any exploit available.
You should upgrade the affected component.