在文章中，李康旭展示了一个实验：通过仅 2 次 API 调用 + 35 行 Python 代码，成功推断出了OpenAI Codex CLI 的上下文压缩流程，并通过一次 prompt injection，诱导模型泄露了内部提示词结构。

PandasAI, an open source project by SinaptikAI, has been found vulnerable to Prompt Injection attacks. An attacker with access to the chat prompt can craft malicious input that is interpreted as code, ...

In context: Prompt injection is an inherent flaw in large language models, allowing attackers to hijack AI behavior by embedding malicious commands in the input text. Most defenses rely on internal ...

Large language models used in artificial intelligence, such as ChatGPT or Google Bard, are prone to different cybersecurity attacks, in particular prompt injection and data poisoning. The U.K.’s ...

OpenAI's brand new Atlas browser is more than willing to follow commands maliciously embedded in a web page, an attack type known as indirect prompt injection.… Prompt injection vulnerability is a ...